© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 11891
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or investigative contexts, particularly focusing on evidence, beliefs, and questioning

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to belief and the implications of authority or law enforcement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jri
    -0.74
     Quan
    -0.73
    .:
    -0.70
    !:
    -0.69
    :#
    -0.64
    *:
    -0.64
    ansky
    -0.64
    .--
    -0.64
    ipel
    -0.63
    :,
    -0.62
    POSITIVE LOGITS
    pires
    0.75
    pired
    0.69
     )]
    0.61
     ostensibly
    0.59
    ELD
    0.58
     intercourse
    0.57
     paycheck
    0.56
     ])
    0.55
     Columb
    0.55
    object
    0.54
    Activations Density 0.747%

    No Known Activations