© 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. 10-RES-JB
    11. 21794
    Prev
    Next
    INDEX
    Explanations

    locations or entities with names that start with "W"

    oai_token-act-pair · gpt-3.5-turbo

    specific mentions of the letter combination 'W' or names that start with 'W'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DEFENSE
    -0.66
    ħĭ
    -0.63
     moons
    -0.61
    advertisement
    -0.60
    ãĥ¼ãĥĨ
    -0.59
    vantage
    -0.58
     Sapphire
    -0.56
    ãĤ¶
    -0.56
    ij士
    -0.55
    £ı
    -0.55
    POSITIVE LOGITS
    ipeg
    1.09
    nesday
    1.07
    ÅĤ
    1.03
    hester
    0.92
    bledon
    0.90
    atche
    0.85
    itzer
    0.82
    zb
    0.80
    bley
    0.79
    risome
    0.78
    Activations Density 0.103%

    No Known Activations