Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 9146
    Prev
    Next
    INDEX
    Explanations

    mentions of legal issues or criminal activities involving individuals

    oai_token-act-pair · gpt-3.5-turbo

    subjects and their actions in a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    birth
    -0.73
    growth
    -0.71
    mop
    -0.70
    tnc
    -0.69
    ysc
    -0.69
    æĦ
    -0.68
    uers
    -0.67
    alg
    -0.67
    Template
    -0.65
     prophecy
    -0.63
    POSITIVE LOGITS
     pleaded
    1.65
     pled
    1.53
     sentenced
    1.46
     convicted
    1.38
     indicted
    1.35
     guilty
    1.35
    Prosecutors
    1.33
     plead
    1.31
     jailed
    1.30
     defendants
    1.27
    Activations Density 0.294%

    No Known Activations