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. 8-RES-JB
    6. 15499
    Prev
    Next
    INDEX
    Explanations

    content related to social media posts and interactions

    oai_token-act-pair · gpt-3.5-turbo

    informal communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ¥µ
    -0.88
    âĢij
    -0.86
    ,—
    -0.74
     glim
    -0.70
    FactoryReloaded
    -0.69
    ersen
    -0.68
    —"
    -0.65
    Footnote
    -0.64
    ¶
    -0.64
    —
    -0.63
    POSITIVE LOGITS
     @
    1.40
     pics
    1.12
     #
    1.11
     congr
    1.08
    sic
    1.07
    ðŁĺ
    1.05
     ðŁij
    1.03
    DonaldTrump
    1.02
     twitter
    1.01
    ðŁ
    1.00
    Activations Density 0.546%

    No Known Activations