© 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. 4-RES-JB
    11. 18643
    Prev
    Next
    INDEX
    Explanations

    self-referential language, such as words that indicate self-identity or self-perception

    oai_token-act-pair · gpt-3.5-turbo

    references to self-identification and personal perspective

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

    No Comments

    Negative Logits
     Meth
    -0.70
    --+
    -0.67
     airst
    -0.62
     Lear
    -0.61
     Via
    -0.61
     methamphetamine
    -0.60
    ARB
    -0.60
     Madden
    -0.60
     frogs
    -0.59
    ////
    -0.59
    POSITIVE LOGITS
    limits
    0.76
    zbek
    0.75
    ãĥ¤
    0.72
    tical
    0.69
    animous
    0.69
    priv
    0.68
    agi
    0.67
     favorably
    0.66
    ilitarian
    0.66
    polit
    0.66
    Activations Density 0.135%

    No Known Activations