© 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. 1304
    Prev
    Next
    INDEX
    Explanations

    adjectives emphasizing degree or quality such as "very."

    oai_token-act-pair · gpt-3.5-turbo

    intensifiers or modifiers indicating high levels of quality or importance

    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
    ula
    -0.65
     rein
    -0.63
     toll
    -0.61
     ditch
    -0.60
     licensing
    -0.60
    din
    -0.60
     autom
    -0.59
     ahead
    -0.59
    uary
    -0.59
    edd
    -0.58
    POSITIVE LOGITS
     Very
    3.04
    Very
    2.59
    very
    1.74
     VERY
    1.67
     Excellent
    1.64
     Quite
    1.62
     Highly
    1.55
     Extreme
    1.54
    Extreme
    1.53
    Excellent
    1.49
    Activations Density 0.026%

    No Known Activations