© 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. 6-RES-JB
    11. 7108
    Prev
    Next
    INDEX
    Explanations

    names containing the string "low"

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals with the surname "Low."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andise
    -0.82
    ãĤ·ãĥ£
    -0.76
    ä½ľ
    -0.75
    natureconservancy
    -0.74
    clave
    -0.73
    issors
    -0.70
    asio
    -0.70
    andum
    -0.69
    arium
    -0.68
    Asia
    -0.66
    POSITIVE LOGITS
    ered
    1.23
    enthal
    0.99
    down
    0.96
    est
    0.94
    ering
    0.91
    rey
    0.91
    enstein
    0.88
    brow
    0.83
    urst
    0.81
    downs
    0.80
    Activations Density 0.024%

    No Known Activations