© 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. 1-RES-JB
    11. 3597
    Prev
    Next
    INDEX
    Explanations

    proper nouns of famous individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to David Bowie and other notable musicians

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itia
    -0.79
    ICAN
    -0.74
    ãĥ¼ãĥĨ
    -0.72
    hesis
    -0.72
    ittee
    -0.68
    ocratic
    -0.67
    ugu
    -0.66
    idential
    -0.65
    unct
    -0.64
    aired
    -0.64
    POSITIVE LOGITS
     Bowie
    1.47
    ellery
    0.81
    querque
    0.76
    knife
    0.74
    Artist
    0.72
    @#&
    0.72
     Spears
    0.67
    annon
    0.67
    rock
    0.66
     Sands
    0.66
    Activations Density 0.015%

    No Known Activations