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

    Neuronpedia

    Jacobian LensNEW
    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. 3852
    Prev
    Next
    INDEX
    Explanations

    words related to familiarity or recognition

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "familiar."

    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
    ©¶æ
    -0.78
    chance
    -0.78
    hap
    -0.75
    hemy
    -0.73
    chnology
    -0.71
    reme
    -0.69
    tan
    -0.69
    prus
    -0.69
    Rog
    -0.69
    application
    -0.68
    POSITIVE LOGITS
     familiar
    0.90
    isable
    0.89
    izations
    0.87
    iliar
    0.87
    sworth
    0.87
    igan
    0.85
    ized
    0.84
    izing
    0.82
    ity
    0.81
    ization
    0.80
    Activations Density 0.018%

    No Known Activations