© 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. 10-RES-JB
    11. 12467
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically movie titles and names of actors or characters

    oai_token-act-pair · gpt-3.5-turbo

    references to films and film-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     podium
    -0.79
     notation
    -0.76
     PSU
    -0.72
     benches
    -0.71
     exch
    -0.70
     disadvantage
    -0.69
     markup
    -0.68
    ibly
    -0.66
     synt
    -0.66
     moderators
    -0.66
    POSITIVE LOGITS
     Clockwork
    0.96
     Chronicles
    0.92
    arenthood
    0.91
     Goodbye
    0.91
     Girl
    0.90
     Deadly
    0.89
     Falling
    0.88
     Diary
    0.88
     Wedding
    0.88
    renheit
    0.87
    Activations Density 0.292%

    No Known Activations