© 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. 3-RES-JB
    11. 12105
    Prev
    Next
    INDEX
    Explanations

    references to physical objects related to writing or organizing thoughts, such as notebooks and pens

    oai_token-act-pair · gpt-3.5-turbo

    mentions of notebooks and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rer
    -0.90
    rie
    -0.88
    tale
    -0.86
    bots
    -0.86
    inations
    -0.84
    rum
    -0.83
    idi
    -0.82
    riages
    -0.82
    amount
    -0.82
    bed
    -0.80
    POSITIVE LOGITS
    externalActionCode
    0.87
     EDT
    0.80
     tee
    0.78
    CRIP
    0.73
    manship
    0.70
     HK
    0.68
     WS
    0.67
     Ryder
    0.66
    tnc
    0.66
     drinking
    0.62
    Activations Density 0.026%

    No Known Activations