© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 36068
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific focal point or central aspect in various contexts or scenarios

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    216
    +0.11
    0.8%
    288
    +0.07
    0.5%
    503
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.24
    326
    +0.07
    0.20
    216
    +0.07
    0.08
    Negative Logits
    eem
    -0.44
     inhibitors
    -0.44
    Downloadha
    -0.43
    utics
    -0.42
     assimil
    -0.41
    cham
    -0.41
     Beautiful
    -0.40
     Incarn
    -0.40
    Sil
    -0.40
    ippery
    -0.40
    POSITIVE LOGITS
     focal
    0.64
    ãĥĥãĤ¯
    0.57
    istics
    0.51
    rang
    0.50
     point
    0.50
    rier
    0.50
    rament
    0.49
    ities
    0.48
    rative
    0.48
    imation
    0.48
    Activations Density 7.172%

    No Known Activations