© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 6576
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases indicating actions carried out separately or individually

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "independently."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nieto
    -0.92
    mers
    -0.81
    risome
    -0.80
    ttp
    -0.78
     Naples
    -0.73
    mer
    -0.73
    MER
    -0.72
    frey
    -0.71
    nery
    -0.71
     Desert
    -0.69
    POSITIVE LOGITS
     minded
    0.92
     contractors
    0.89
    ially
    0.88
    wine
    0.87
    heses
    0.86
    handedly
    0.85
     corrobor
    0.83
     contractor
    0.82
     verified
    0.78
    lect
    0.76
    Activations Density 0.012%

    No Known Activations