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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 20612
    Prev
    Next
    INDEX
    Explanations

    words related to legal charges and criminal offenses

    oai_token-act-pair · gpt-3.5-turbo

    references to degrees of serious criminal charges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TAG
    -0.63
     unprotected
    -0.63
    sel
    -0.61
     Tycoon
    -0.61
    joined
    -0.61
    KEN
    -0.61
     Pengu
    -0.60
    imon
    -0.59
    ded
    -0.58
    sels
    -0.58
    POSITIVE LOGITS
    degree
    1.26
     degrees
    1.01
    renheit
    0.95
     Celsius
    0.94
     degree
    0.91
     Degree
    0.86
    rees
    0.82
    anced
    0.81
     ILCS
    0.80
    ance
    0.80
    Activations Density 0.007%

    No Known Activations