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. 7422
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions that involve guiding, forming, or influencing something

    oai_token-act-pair · gpt-3.5-turbo

    actions related to initiating, developing, or contributing to processes or agendas

    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
    arij
    -0.75
     externalToEVAOnly
    -0.72
    -----------
    -0.67
     =================================
    -0.66
     Appears
    -0.63
    Downloadha
    -0.63
     interfered
    -0.62
    Publisher
    -0.62
    advertisement
    -0.62
    Nothing
    -0.60
    POSITIVE LOGITS
    uate
    0.83
    balance
    0.71
    erning
    0.65
    enance
    0.62
     perceptions
    0.61
    idon
    0.61
    burse
    0.60
    ocker
    0.60
    veland
    0.60
     budding
    0.60
    Activations Density 0.159%

    No Known Activations