© 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. 1-RES-JB
    11. 20179
    Prev
    Next
    INDEX
    Explanations

    references to funding or financial support

    oai_token-act-pair · gpt-3.5-turbo

    references to funding or financial support

    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
    alter
    -0.79
    apple
    -0.77
    ijn
    -0.77
    vent
    -0.74
    Son
    -0.71
    bourne
    -0.70
    iPhone
    -0.70
    xious
    -0.69
    Scot
    -0.69
     Spice
    -0.69
    POSITIVE LOGITS
     funded
    1.18
     financed
    1.17
    funded
    0.90
     funding
    0.88
     arming
    0.80
    nesday
    0.79
    ometimes
    0.76
    ensibly
    0.75
    interstitial
    0.75
     fundra
    0.75
    Activations Density 0.006%

    No Known Activations