© 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. 11-RES-JB
    11. 9887
    Prev
    Next
    INDEX
    Explanations

    terms related to specific names (likely related to sports)

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to people and locations within the context of cryptocurrency and its developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ£
    -0.65
     Scotia
    -0.65
     Bundy
    -0.60
    ivities
    -0.58
     Carbuncle
    -0.56
    omial
    -0.56
    istic
    -0.55
     CPC
    -0.55
    apter
    -0.54
     Franch
    -0.53
    POSITIVE LOGITS
    eki
    0.89
    eco
    0.89
    hene
    0.89
    hest
    0.88
    riter
    0.84
    say
    0.84
    sie
    0.84
    ENE
    0.78
    ahl
    0.77
    hurst
    0.77
    Activations Density 0.096%

    No Known Activations