© 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. 4-RES-JB
    11. 10061
    Prev
    Next
    INDEX
    Explanations

    phrases related to speed or growth

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to fast-moving or rapidly growing industries or trends

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

    No Comments

    Negative Logits
    Lenin
    -0.82
    ById
    -0.78
    Ö¼
    -0.75
     Contributions
    -0.73
     Refuge
    -0.68
    è£
    -0.68
    å·
    -0.68
    è»
    -0.68
     likeness
    -0.65
     sep
    -0.65
    POSITIVE LOGITS
    twitch
    0.88
    charging
    0.79
    ounters
    0.73
    multipl
    0.72
     paced
    0.71
    duration
    0.71
    odic
    0.70
    alore
    0.68
     uptake
    0.68
     Furious
    0.68
    Activations Density 0.208%

    No Known Activations