© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 20845
    Prev
    Next
    INDEX
    Explanations

    references to written columns or articles in publications

    oai_token-act-pair · gpt-3.5-turbo

    references to opinion columns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ramid
    -0.71
    qual
    -0.70
    zie
    -0.67
    lder
    -0.67
    CRIP
    -0.66
    VE
    -0.66
    foot
    -0.65
    ccording
    -0.64
    ETH
    -0.64
     Norn
    -0.63
    POSITIVE LOGITS
     columns
    1.25
     column
    1.21
    column
    0.98
     Column
    0.95
    iers
    0.82
    oad
    0.79
    ials
    0.76
    Column
    0.76
    igible
    0.75
    antry
    0.75
    Activations Density 0.009%

    No Known Activations