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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 14607
    Prev
    Next
    INDEX
    Explanations

    phrases related to hierarchy or sequence

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate hierarchy or order within a system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iland
    -0.71
     contrace
    -0.68
    >[
    -0.66
     Sachs
    -0.63
    zinski
    -0.63
    furt
    -0.61
    internet
    -0.61
    gow
    -0.59
     prevailing
    -0.59
     ',
    -0.57
    POSITIVE LOGITS
     magnitude
    0.97
     Cthulhu
    0.96
     precedence
    0.96
    lege
    0.88
     Duty
    0.87
    rontal
    0.86
     duty
    0.81
    aiden
    0.79
    redo
    0.74
    alions
    0.74
    Activations Density 0.097%

    No Known Activations