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. 7-RES-JB
    6. 8371
    Prev
    Next
    INDEX
    Explanations

    connectors that contrast ideas

    oai_token-act-pair · gpt-3.5-turbo

    ideas that challenge conventional beliefs about individualism and success

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interstitial
    -0.81
    åĮ
    -0.70
    Eva
    -0.69
     awoken
    -0.66
    ãģ®ç
    -0.66
    inarily
    -0.66
     +++
    -0.64
    cellaneous
    -0.63
    )))
    -0.63
    00007
    -0.62
    POSITIVE LOGITS
     nor
    1.02
     necessarily
    1.01
     anymore
    0.96
    \":
    0.70
    teness
    0.70
     malice
    0.67
    ASY
    0.64
     merits
    0.63
     any
    0.63
     anybody
    0.62
    Activations Density 0.583%

    No Known Activations