© 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. 15480
    Prev
    Next
    INDEX
    Explanations

    code snippets related to writing lines to the console

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly the period

    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
     conflic
    -0.86
    ccording
    -0.74
    Leaks
    -0.73
     quo
    -0.73
     confir
    -0.72
     therap
    -0.71
    wagen
    -0.68
     Leilan
    -0.67
    soever
    -0.66
    rers
    -0.66
    POSITIVE LOGITS
     .
    0.76
     Stub
    0.73
    NET
    0.72
    ini
    0.70
    domain
    0.68
     mk
    0.67
    prototype
    0.66
    avi
    0.65
    google
    0.65
     ._
    0.64
    Activations Density 0.033%

    No Known Activations