© 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. 3-RES-JB
    11. 10805
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to companies or organizations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Big" followed by numerical values, particularly those referring to groups or organizations

    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
     confir
    -0.94
    idency
    -0.87
    anwhile
    -0.86
    yrim
    -0.82
    Downloadha
    -0.78
    theless
    -0.77
    veyard
    -0.73
     guiActiveUn
    -0.73
    istry
    -0.72
    izabeth
    -0.71
    POSITIVE LOGITS
    gest
    1.29
    ger
    1.14
    glers
    0.87
    ging
    0.86
    gers
    0.85
    gins
    0.84
     Brother
    0.83
    gie
    0.83
    Integer
    0.81
     Daddy
    0.78
    Activations Density 0.017%

    No Known Activations