© 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. 9-RES-JB
    11. 15532
    Prev
    Next
    INDEX
    Explanations

    text related to political consultations, commitments, and affiliations

    oai_token-act-pair · gpt-3.5-turbo

    symbols or characters that indicate formatting or coding issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     accomp
    -0.63
     Imper
    -0.62
     mash
    -0.62
     encount
    -0.59
     crus
    -0.58
     wors
    -0.57
     denomin
    -0.56
     magn
    -0.56
     Trojan
    -0.56
     backdrop
    -0.56
    POSITIVE LOGITS
    him
    1.20
    them
    1.10
    their
    1.04
    his
    0.95
    selves
    0.94
    gently
    0.92
    onto
    0.92
    DERR
    0.89
    your
    0.85
    ationally
    0.85
    Activations Density 0.312%

    No Known Activations