© 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. 12213
    Prev
    Next
    INDEX
    Explanations

    instances where something is inaccessible or beyond reach

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "unable."

    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
    soType
    -0.78
     Tradition
    -0.74
    soDeliveryDate
    -0.70
    lique
    -0.68
    gone
    -0.68
    nice
    -0.67
    RAFT
    -0.64
    VERTISEMENT
    -0.64
    agate
    -0.62
    email
    -0.62
    POSITIVE LOGITS
     compe
    0.95
    ioned
    0.93
    poke
    0.79
    icably
    0.78
     necessarily
    0.77
     adequately
    0.75
    ison
    0.75
    untarily
    0.74
    phy
    0.72
    urred
    0.72
    Activations Density 0.022%

    No Known Activations