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. 0-RES-JB
    6. 945
    Prev
    Next
    INDEX
    Explanations

    Twitter usernames

    oai_token-act-pair · gpt-3.5-turbo

    the presence of social media handles or mentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Icar
    -0.63
     consolidation
    -0.61
     partly
    -0.61
     coax
    -0.58
     Takeru
    -0.55
     cigarette
    -0.53
     sterile
    -0.53
     stricken
    -0.53
     wholes
    -0.53
     dirt
    -0.53
    POSITIVE LOGITS
     (@
    4.12
     ðŁ
    1.62
    ðŁ
    1.52
     @
    1.50
    ï¸ı
    1.46
     tweeted
    1.39
     "@
    1.38
     (#
    1.37
     âľ
    1.35
     ðŁij
    1.35
    Activations Density 0.023%

    No Known Activations