© 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. 3-RES-JB
    11. 13561
    Prev
    Next
    INDEX
    Explanations

    references to the character "James Bond"

    oai_token-act-pair · gpt-3.5-turbo

    references to the James Bond franchise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ³ãĤ¸
    -0.90
    OURCE
    -0.83
    itably
    -0.82
    resents
    -0.77
    NPR
    -0.76
    oaded
    -0.72
    seless
    -0.72
    à¼
    -0.71
    ãĥ£
    -0.68
    KNOWN
    -0.68
    POSITIVE LOGITS
     Bond
    1.17
     Bonds
    0.93
    eson
    0.81
    sov
    0.81
    minster
    0.80
     Rib
    0.79
    holes
    0.77
    ing
    0.76
    wana
    0.72
    erm
    0.72
    Activations Density 0.009%

    No Known Activations