© 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. 3-RES-JB
    11. 23704
    Prev
    Next
    INDEX
    Explanations

    famous names, especially musicians and athletes

    oai_token-act-pair · gpt-3.5-turbo

    names of notable public figures, particularly entertainers and athletes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.74
    Els
    -0.71
    Maria
    -0.71
    Methods
    -0.64
    Region
    -0.64
    Others
    -0.64
    ivity
    -0.63
    depend
    -0.63
     Mae
    -0.62
    REAM
    -0.62
    POSITIVE LOGITS
    steen
    0.90
    agher
    0.83
    hler
    0.79
    enei
    0.78
     Presents
    0.74
     replacing
    0.71
     taught
    0.70
    cknow
    0.69
    bourg
    0.69
     oath
    0.69
    Activations Density 0.266%

    No Known Activations