© 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. 8-RES-JB
    11. 871
    Prev
    Next
    INDEX
    Explanations

    numerical references and timestamps

    oai_token-act-pair · gpt-3.5-turbo

    references to sequential or upcoming elements, such as chapters, games, or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nered
    -0.84
    ocker
    -0.73
    otten
    -0.70
    ouf
    -0.69
    leeve
    -0.69
    76561
    -0.68
    esse
    -0.67
     alike
    -0.67
    effic
    -0.66
    otto
    -0.63
    POSITIVE LOGITS
     installments
    0.71
     installment
    0.71
    enium
    0.70
     onwards
    0.68
     generations
    0.64
     refres
    0.63
     Generations
    0.62
    UTE
    0.60
     Micha
    0.59
    tta
    0.59
    Activations Density 0.132%

    No Known Activations