© 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. 8-RES-JB
    11. 3120
    Prev
    Next
    INDEX
    Explanations

    long phrases or sentences related to technological processes or scenarios

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to learning and processes involving time or stages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    %]
    -0.74
    ounding
    -0.71
    ums
    -0.68
    vana
    -0.63
    isu
    -0.62
    habi
    -0.62
    MOD
    -0.62
    resa
    -0.61
    instein
    -0.61
    egu
    -0.60
    POSITIVE LOGITS
     they
    1.13
     there
    1.00
     we
    0.99
     it
    0.95
     THEY
    0.92
     THERE
    0.88
     he
    0.87
    there
    0.82
    they
    0.82
     nobody
    0.81
    Activations Density 0.571%

    No Known Activations