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. 34643
    Prev
    Next
    INDEX
    Explanations

    information related to Earth and space, such as geological phenomena and space missions

    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
    393
    +0.10
    0.5%
    629
    +0.09
    0.5%
    549
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.10
    0.25
    608
    +0.09
    0.29
    393
    +0.09
    0.34
    Negative Logits
    SPONSORED
    -0.77
    awaru
    -0.68
    DragonMagazine
    -0.61
    uly
    -0.60
    soever
    -0.58
    loo
    -0.58
     behav
    -0.56
    çīĪ
    -0.55
     ancest
    -0.55
    ©¶æ
    -0.55
    POSITIVE LOGITS
    clusions
    0.69
    roads
    0.61
    enough
    0.59
     stature
    0.56
    versions
    0.55
    tics
    0.53
    board
    0.53
     quantity
    0.52
    feld
    0.52
    entin
    0.51
    Activations Density 13.730%

    No Known Activations