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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14254
    Prev
    Next
    INDEX
    Explanations

    references to numbers related to technical specifications and amounts in a document

    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
    218
    +0.03
    0.6%
    314
    +0.02
    0.5%
    10
    +0.02
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    570
    +0.03
    0.02
    230
    +0.02
    0.09
    95
    +0.02
    0.08
    Negative Logits
     Hasan
    -0.13
     Bened
    -0.13
     governor
    -0.13
    ocalypse
    -0.13
    alid
    -0.13
    hatt
    -0.12
    ason
    -0.12
    waters
    -0.12
    hner
    -0.12
     chancellor
    -0.12
    POSITIVE LOGITS
     certs
    0.18
     pounds
    0.18
     lbs
    0.18
     000
    0.17
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.17
     litres
    0.16
     kg
    0.16
     calories
    0.16
    lbs
    0.15
    escent
    0.15
    Activations Density 9.636%

    No Known Activations