© 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. 18476
    Prev
    Next
    INDEX
    Explanations

    words related to medical diagnostics or technical processes involving monitoring and analysis

    oai_token-act-pair · gpt-3.5-turbo

    terms related to prognostics and predictions

    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
     Dickens
    -0.67
     GOODMAN
    -0.64
    lift
    -0.63
     fingerprints
    -0.63
    footed
    -0.63
    cule
    -0.63
     Heist
    -0.62
    shapeshifter
    -0.62
    ĸļ
    -0.61
     palms
    -0.61
    POSITIVE LOGITS
    nostic
    1.30
    nosis
    1.10
    rade
    1.02
    ceed
    0.97
    etric
    0.94
     prog
    0.93
    rad
    0.90
    eny
    0.87
    resso
    0.84
    ester
    0.82
    Activations Density 0.022%

    No Known Activations