© 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 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. 7-RES-JB
    11. 24082
    Prev
    Next
    INDEX
    Explanations

    government-related entities, such as various attorney offices

    oai_token-act-pair · gpt-3.5-turbo

    references to various attorney offices and legal authorities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zl
    -0.79
    pless
    -0.73
    bull
    -0.70
    "]=>
    -0.69
    Ku
    -0.69
    stream
    -0.67
    adapt
    -0.67
    origin
    -0.66
    æĦ
    -0.65
    asted
    -0.65
    POSITIVE LOGITS
     Office
    0.81
     Prosecutor
    0.78
     Marshal
    0.75
     indicted
    0.74
     prosecutor
    0.73
     Deputy
    0.73
     deputy
    0.72
     investigating
    0.71
    ial
    0.70
     Commissioner
    0.70
    Activations Density 0.055%

    No Known Activations