© 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. 36238
    Prev
    Next
    INDEX
    Explanations

    descriptions related to high-end products, industries, or experiences

    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
    447
    +0.25
    1.4%
    270
    +0.08
    0.4%
    195
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    426
    +0.25
    0.05
    88
    +0.08
    0.06
    270
    +0.07
    0.03
    Negative Logits
    çİĭ
    -0.61
    ichick
    -0.60
    atoon
    -0.60
    pload
    -0.58
    в
    -0.58
    ãĤ¼ãĤ¦ãĤ¹
    -0.55
     Walls
    -0.54
     Haley
    -0.52
    leader
    -0.52
    rek
    -0.51
    POSITIVE LOGITS
     consumer
    0.69
     earners
    0.67
    Performance
    0.65
    urance
    0.65
     models
    0.63
     discretionary
    0.62
    uries
    0.61
    umers
    0.58
     hardware
    0.58
    ering
    0.58
    Activations Density 9.911%

    No Known Activations