© 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. 12841
    Prev
    Next
    INDEX
    Explanations

    special characters and computer programming language syntax

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically commas

    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
    natureconservancy
    -0.73
    interstitial
    -0.71
     exha
    -0.70
    conom
    -0.69
     unnecess
    -0.69
    uggest
    -0.67
     perspect
    -0.67
     footing
    -0.66
     behavi
    -0.66
     corrid
    -0.66
    POSITIVE LOGITS
     etc
    1.05
     huh
    0.95
     eh
    0.85
     however
    0.82
     supra
    0.79
     please
    0.78
     aka
    0.76
     et
    0.74
    )"
    0.74
    032
    0.73
    Activations Density 1.525%

    No Known Activations