© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 5841
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names followed by possessive markers

    oai_token-act-pair · gpt-3.5-turbo

    references to entities or things that are characterized as "the biggest," "the most," or other superlative terms

    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
    icz
    -0.74
    =~
    -0.73
    gery
    -0.70
    someone
    -0.69
     Norn
    -0.69
    ariat
    -0.65
    fecture
    -0.65
    ogle
    -0.65
     ..............
    -0.65
    }}}
    -0.64
    POSITIVE LOGITS
     favourites
    1.03
     strengths
    0.98
     favorites
    0.96
     finest
    0.96
     favourite
    0.96
     busiest
    0.93
     greatest
    0.90
     favorite
    0.88
     favoured
    0.88
     notable
    0.87
    Activations Density 0.066%

    No Known Activations