© 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. 16844
    Prev
    Next
    INDEX
    Explanations

    references to research studies and findings

    oai_token-act-pair · gpt-3.5-turbo

    references to researchers and their activities

    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
    BuyableInstoreAndOnline
    -0.76
     Rapids
    -0.70
    Enough
    -0.65
     Leilan
    -0.63
    times
    -0.62
    stones
    -0.59
     Maiden
    -0.59
     Flames
    -0.58
    icative
    -0.57
    erous
    -0.57
    POSITIVE LOGITS
    Researchers
    0.97
     Researchers
    0.94
     studying
    0.93
    hips
    0.87
    sonian
    0.85
     specializing
    0.83
     researching
    0.83
     researcher
    0.82
     researchers
    0.81
     scientist
    0.81
    Activations Density 0.045%

    No Known Activations