Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 19950
    Prev
    Next
    INDEX
    Explanations

    expressions related to being at home and specific moments or items connected to the home setting

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal experiences and feelings related to being alone

    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
     guiName
    -0.83
    ãĢİ
    -0.55
    ":[{"
    -0.53
    verages
    -0.47
    byss
    -0.43
    ãĢIJ
    -0.43
     (?,
    -0.43
    ADVERTISEMENT
    -0.42
    ":["
    -0.42
    Newsletter
    -0.42
    POSITIVE LOGITS
    )."
    2.39
    ?).
    2.38
    ?)
    2.38
    ').
    2.37
    !)
    2.35
    !).
    2.35
    ?),
    2.30
    ')
    2.29
    ),"
    2.28
    !),
    2.27
    Activations Density 1.696%

    No Known Activations