© 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. 3-RES-JB
    11. 11965
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to businesses, organizations, and individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate leadership or being at the forefront in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ombies
    -0.78
    agen
    -0.69
    rehens
    -0.69
    ager
    -0.65
    agan
    -0.65
    cube
    -0.64
    aves
    -0.64
    hemy
    -0.64
    ope
    -0.64
    afort
    -0.63
    POSITIVE LOGITS
     Leading
    0.95
    boards
    0.88
     leading
    0.85
    better
    0.81
    wcs
    0.79
    quartered
    0.79
     scorer
    0.74
    lines
    0.74
    lined
    0.73
    lead
    0.72
    Activations Density 0.024%

    No Known Activations