© 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. 3-RES-JB
    11. 13287
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a location or spatial relationship

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "in."

    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
     VIDEOS
    -0.87
    Fs
    -0.66
     accompanies
    -0.65
    Father
    -0.64
    SHIP
    -0.63
    Skip
    -0.63
     Emails
    -0.63
     enhances
    -0.63
     reduces
    -0.62
     thereafter
    -0.62
    POSITIVE LOGITS
    urated
    0.94
    liest
    0.90
    ivable
    0.88
    omorphic
    0.87
    ivated
    0.85
    atile
    0.80
    cluded
    0.80
    dden
    0.77
    uble
    0.76
    igmatic
    0.75
    Activations Density 0.673%

    No Known Activations