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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 45826
    Prev
    Next
    INDEX
    Explanations

    content related to rankings, positions, and numbers in various contexts

    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
    314
    +0.13
    0.6%
    686
    +0.09
    0.5%
    173
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.13
    -0.01
    127
    +0.09
    0.08
    676
    +0.09
    0.12
    Negative Logits
     Gors
    -0.76
     destro
    -0.75
     trave
    -0.74
     provoking
    -0.69
     concentrating
    -0.68
     cler
    -0.66
     sacrific
    -0.64
     fatig
    -0.64
     seiz
    -0.63
     condem
    -0.63
    POSITIVE LOGITS
    ###
    0.94
    DIV
    0.92
    #$
    0.90
    DNA
    0.89
    @#
    0.89
    ABC
    0.89
    !/
    0.86
    @@@@@@@@
    0.83
    ################
    0.82
    âĢİ
    0.82
    Activations Density 8.446%

    No Known Activations