© 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. 7095
    Prev
    Next
    INDEX
    Explanations

    information related to release dates and details about products or events

    oai_token-act-pair · gpt-3.5-turbo

    information related to video game releases and retail details

    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
    apego
    -0.73
    yll
    -0.70
    ndra
    -0.70
    icult
    -0.69
    uliffe
    -0.68
    adier
    -0.67
     improvised
    -0.66
     instinct
    -0.66
    vec
    -0.65
     youthful
    -0.63
    POSITIVE LOGITS
     TBA
    1.07
    iversary
    0.97
    Xbox
    0.91
     2019
    0.89
     NX
    0.85
     Deadline
    0.84
     PAX
    0.83
    GMT
    0.82
     Ubisoft
    0.81
     TBD
    0.81
    Activations Density 0.603%

    No Known Activations