© 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. 9-RES-JB
    11. 2475
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing an overall positive or negative assessment or recommendation

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Caf
    -0.72
    bley
    -0.66
    DragonMagazine
    -0.65
    fif
    -0.65
     Bry
    -0.64
     Frie
    -0.64
    poons
    -0.64
    yond
    -0.64
    cells
    -0.64
     Feld
    -0.63
    POSITIVE LOGITS
     picture
    0.84
     stability
    0.84
     attractiveness
    0.83
     satisfaction
    0.82
     usefulness
    0.82
     outlook
    0.80
     length
    0.80
     impression
    0.79
     wellbeing
    0.79
     effectiveness
    0.77
    Activations Density 0.034%

    No Known Activations