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. 4-RES-JB
    6. 17853
    Prev
    Next
    INDEX
    Explanations

    phrases related to movement and actions

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions or repeated phrases indicating continuity in actions

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

    No Comments

    Negative Logits
    panel
    -0.75
    Times
    -0.70
    MK
    -0.70
    NULL
    -0.68
    Deal
    -0.67
    ADVERTISEMENT
    -0.67
    United
    -0.67
    unique
    -0.66
    BC
    -0.65
    entials
    -0.65
    POSITIVE LOGITS
     then
    0.97
     consequently
    0.94
     therefore
    0.91
     thus
    0.90
     thence
    0.90
    rogen
    0.89
     secondly
    0.85
     THEN
    0.82
     possibly
    0.82
     hopefully
    0.81
    Activations Density 0.509%

    No Known Activations