Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-RES-JB
    6. 9745
    Prev
    Next
    INDEX
    Explanations

    words related to time periods or sequences such as "post-1973" or "post-credit"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating periods or conditions following significant events or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     outnumbered
    -0.83
     chants
    -0.78
     Wanted
    -0.76
     nick
    -0.66
     Qiao
    -0.66
     Rivals
    -0.63
     alone
    -0.63
     sorely
    -0.63
     Cohn
    -0.62
     weights
    -0.62
    POSITIVE LOGITS
    mortem
    1.59
    processing
    1.33
    election
    1.31
    traumatic
    1.28
    industrial
    1.18
    mort
    1.17
    doctoral
    1.17
    production
    1.15
    secondary
    1.15
    natal
    1.13
    Activations Density 0.028%

    No Known Activations