© 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. 0-RES-JB
    11. 2853
    Prev
    Next
    INDEX
    Explanations

    dates and titles related to music releases

    oai_token-act-pair · gpt-3.5-turbo

    titles and information related to music releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     largeDownload
    -0.75
    ãĥģ
    -0.66
    Figure
    -0.64
     Galile
    -0.63
     standpoint
    -0.63
     offset
    -0.62
    External
    -0.62
    âĤ¬
    -0.61
     unpublished
    -0.61
    Spanish
    -0.59
    POSITIVE LOGITS
     Releases
    1.40
    omas
    1.18
    les
    0.89
    osponsors
    0.82
    etts
    0.80
    ema
    0.76
    endas
    0.74
    breaks
    0.73
    ategor
    0.71
    chens
    0.71
    Activations Density 0.003%

    No Known Activations