© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 19368
    Prev
    Next
    INDEX
    Explanations

    names of specific individuals or locations, particularly Greene County and Kathleen Wynne

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of specific names, particularly in a context related to controversies or events

    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
    abad
    -0.84
    inations
    -0.83
    ÑĮ
    -0.83
    imony
    -0.82
    omial
    -0.81
    unn
    -0.80
    oric
    -0.79
    ority
    -0.79
    omething
    -0.78
    atars
    -0.76
    POSITIVE LOGITS
     manure
    0.80
     Greene
    0.76
    cloth
    0.65
    keeper
    0.64
    lees
    0.63
    joy
    0.63
     CK
    0.63
     reap
    0.61
     cattle
    0.60
     cart
    0.60
    Activations Density 0.026%

    No Known Activations