© 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. 4041
    Prev
    Next
    INDEX
    Explanations

    uppercase words

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to sharpness or intensity

    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
    hips
    -0.71
    Subscribe
    -0.71
     Consent
    -0.69
    lord
    -0.68
    via
    -0.67
    Via
    -0.66
     Tycoon
    -0.64
     Spons
    -0.63
    enter
    -0.63
    Charl
    -0.62
    POSITIVE LOGITS
     sharp
    3.52
    sharp
    2.43
     sharper
    2.42
    Sharp
    1.84
     Sharp
    1.83
     razor
    1.46
     shar
    1.45
     sharply
    1.36
     stark
    1.25
     crisp
    1.18
    Activations Density 0.018%

    No Known Activations