© 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. 18698
    Prev
    Next
    INDEX
    Explanations

    French names or terms

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Claude" and its variations

    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
    lake
    -0.78
    roxy
    -0.73
    watch
    -0.72
    lar
    -0.66
    BALL
    -0.65
    loaded
    -0.64
     belt
    -0.63
    raid
    -0.62
    PLIED
    -0.62
     indo
    -0.62
    POSITIVE LOGITS
    issance
    0.91
    ude
    0.90
    igue
    0.89
    uty
    0.87
    ues
    0.85
    ottesville
    0.84
    Cla
    0.84
    ignt
    0.83
    herty
    0.83
    udes
    0.82
    Activations Density 0.051%

    No Known Activations