© 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. 6-RES-JB
    11. 18821
    Prev
    Next
    INDEX
    Explanations

    instances of causal relationships and actions leading to specific outcomes

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant events or decisions leading to notable consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾įå¥ij士
    -0.78
    ãĥ¼ãĤ¯
    -0.73
    ITED
    -0.69
    Downloadha
    -0.66
    soever
    -0.65
    ypes
    -0.65
    Previous
    -0.62
    Mouse
    -0.60
    âĸij
    -0.60
     Bowie
    -0.59
    POSITIVE LOGITS
     downfall
    0.89
     paralysis
    0.87
     deterioration
    0.85
     termination
    0.84
     deaths
    0.81
     conversion
    0.80
     realization
    0.80
     conclusion
    0.80
     expulsion
    0.80
     breakdown
    0.79
    Activations Density 0.314%

    No Known Activations