© 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. 2-RES-JB
    11. 12542
    Prev
    Next
    INDEX
    Explanations

    names of individuals associated with various professions

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pradesh
    -0.72
    mits
    -0.72
     Cassandra
    -0.64
    ipper
    -0.64
     Pixie
    -0.63
    FUL
    -0.63
    fulness
    -0.63
     Brazilian
    -0.61
     trooper
    -0.61
    apache
    -0.60
    POSITIVE LOGITS
     Katz
    1.12
    baum
    1.07
    stein
    1.06
    fman
    0.99
     Greenberg
    0.97
     Rosenthal
    0.91
    owitz
    0.90
    stadt
    0.89
     Horowitz
    0.89
     Goodman
    0.89
    Activations Density 0.018%

    No Known Activations