© 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. 13359
    Prev
    Next
    INDEX
    Explanations

    words related to the body or physical sensations

    oai_token-act-pair · gpt-3.5-turbo

    references to personal or possessive pronouns

    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
    itect
    -0.87
    haus
    -0.73
    ocument
    -0.73
    20439
    -0.70
    tar
    -0.70
    âĦ¢:
    -0.67
    ovo
    -0.66
    ãĥ©ãĥ³
    -0.66
    bender
    -0.65
     Logged
    -0.65
    POSITIVE LOGITS
     own
    1.62
     newfound
    1.07
     favourite
    1.03
    selves
    1.03
    self
    1.02
     deepest
    0.97
     favorite
    0.96
     surroundings
    0.96
     knees
    0.95
     superiors
    0.94
    Activations Density 0.517%

    No Known Activations