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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12214
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people or organizations with the prefix "Pr"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the abbreviation "Pr" followed by numbers or certain words

    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
    dayName
    -0.77
    INESS
    -0.71
     EntityItem
    -0.69
    eers
    -0.68
    RAFT
    -0.67
     SOLD
    -0.65
    ãĥ¼ãĥ«
    -0.64
    manship
    -0.64
     spirited
    -0.63
     couch
    -0.63
    POSITIVE LOGITS
    udence
    1.07
    atche
    1.07
    ima
    1.02
    imes
    0.93
    ussia
    0.88
    ud
    0.87
    ag
    0.86
    ussian
    0.86
    ager
    0.85
    acks
    0.85
    Activations Density 0.009%

    No Known Activations