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. 18377
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to norms, standards, or common occurrences

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating general trends or typical behaviors

    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
    htaking
    -0.70
    atures
    -0.69
    Reviewer
    -0.68
    á
    -0.66
    uel
    -0.66
    udi
    -0.63
    ati
    -0.63
    ancer
    -0.63
    arta
    -0.62
    assi
    -0.62
    POSITIVE LOGITS
    entimes
    1.16
     accompanied
    0.90
     consist
    0.90
     abbrevi
    0.85
     involve
    0.85
     preceded
    0.82
     consists
    0.82
     overlooked
    0.82
     followed
    0.81
     referred
    0.81
    Activations Density 0.110%

    No Known Activations