© 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. 16700
    Prev
    Next
    INDEX
    Explanations

    personal statements or confessions

    oai_token-act-pair · gpt-3.5-turbo

    instances of personal reflections or expressions of thought

    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
     predec
    -0.64
     memorable
    -0.64
    ":["
    -0.62
    onso
    -0.61
     confir
    -0.58
     1949
    -0.58
     gem
    -0.57
    ato
    -0.57
     Ended
    -0.57
    oda
    -0.57
    POSITIVE LOGITS
     lately
    1.02
    selves
    0.72
     behalf
    0.66
     awfully
    0.65
    edge
    0.65
     furiously
    0.64
     now
    0.64
     Trends
    0.63
     frantically
    0.63
     footsteps
    0.63
    Activations Density 0.988%

    No Known Activations