© 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. 9205
    Prev
    Next
    INDEX
    Explanations

    verbs related to achievement and success

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "win" in various contexts, particularly related to success or victory

    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
    opian
    -0.68
    hesis
    -0.63
    ãĤ³
    -0.61
    arin
    -0.60
    rete
    -0.59
    eki
    -0.58
    resa
    -0.58
    aven
    -0.57
    address
    -0.56
    rehens
    -0.55
    POSITIVE LOGITS
     hearts
    1.13
    now
    1.13
     championships
    0.96
     elections
    0.93
     prizes
    0.91
     awards
    0.90
     trophies
    0.90
     battles
    0.87
     medals
    0.87
     competitions
    0.85
    Activations Density 0.058%

    No Known Activations