Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 40098
    Prev
    Next
    INDEX
    Explanations

    financial and political information related to large sums of money or government actions

    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
    347
    +0.10
    0.5%
    626
    +0.10
    0.5%
    497
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    127
    +0.10
    0.08
    260
    +0.10
    0.12
    680
    +0.10
    0.08
    Negative Logits
     Uri
    -0.66
    ventus
    -0.65
    alyses
    -0.63
     Gladiator
    -0.61
    Notice
    -0.60
    ateg
    -0.60
    intendent
    -0.60
     Surviv
    -0.60
    IDER
    -0.59
     srfAttach
    -0.59
    POSITIVE LOGITS
     allotted
    0.75
    ottest
    0.71
     dots
    0.71
     mark
    0.70
    liest
    0.69
    odd
    0.65
     confines
    0.64
     allowable
    0.64
     remaining
    0.64
     totality
    0.64
    Activations Density 7.696%

    No Known Activations