© 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. 2-RES-JB
    11. 24124
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases that are separated by a specific symbol pattern Ċ<number>

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and formatting indicators within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    boro
    -0.84
    hement
    -0.74
     hust
    -0.74
     outwe
    -0.73
    atche
    -0.73
    ername
    -0.73
     marching
    -0.73
    uca
    -0.73
     fleeing
    -0.71
     neighb
    -0.70
    POSITIVE LOGITS
    Disclaimer
    1.06
    Example
    1.03
    Recommended
    1.01
    TABLE
    0.99
    Different
    0.99
    Features
    0.96
    Production
    0.95
    Development
    0.95
    Testing
    0.95
    Currently
    0.95
    Activations Density 1.508%

    No Known Activations