© 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. 36540
    Prev
    Next
    INDEX
    Explanations

    terms related to space exploration and technology

    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
    746
    +0.13
    0.6%
    526
    +0.11
    0.5%
    718
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.26
    167
    +0.11
    -0.02
    113
    +0.10
    0.11
    Negative Logits
    ĺħ
    -0.84
    ħĭ
    -0.83
     sender
    -0.67
    ¿½
    -0.65
    theless
    -0.65
     duplication
    -0.64
     fixme
    -0.64
     americ
    -0.60
     bore
    -0.60
     constellation
    -0.60
    POSITIVE LOGITS
    etr
    1.14
    eless
    1.14
    estate
    1.08
    ew
    1.05
    etime
    1.05
    ern
    1.00
    emate
    1.00
    elines
    0.99
    eled
    0.99
    ables
    0.98
    Activations Density 11.330%

    No Known Activations