© 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. 1-RES-JB
    11. 24064
    Prev
    Next
    INDEX
    Explanations

    the word "Councillor" with varying levels of relevance

    oai_token-act-pair · gpt-3.5-turbo

    references to council members and their activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roosevelt
    -0.74
    ARS
    -0.74
     Gamb
    -0.67
    ENGTH
    -0.66
    atics
    -0.66
    çīĪ
    -0.65
     Haram
    -0.64
    ylan
    -0.63
     rooting
    -0.61
     Artemis
    -0.61
    POSITIVE LOGITS
     Coun
    1.38
    cill
    1.35
    Coun
    1.23
    cil
    0.90
     councillors
    0.88
     pse
    0.87
    selling
    0.86
    voy
    0.84
    minist
    0.83
    plin
    0.82
    Activations Density 0.008%

    No Known Activations