© 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. 2-RES-JB
    11. 1377
    Prev
    Next
    INDEX
    Explanations

    mentions of legal proceedings or events, particularly those involving a judge presiding over a case

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "preside" and related actions in legal and formal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wall
    -0.81
    alter
    -0.76
    ables
    -0.73
    acion
    -0.73
    now
    -0.73
    adan
    -0.72
    able
    -0.71
    holders
    -0.71
    ership
    -0.71
    arta
    -0.70
    POSITIVE LOGITS
    ĸļ
    1.13
    nesday
    1.11
    uled
    0.89
     unsuccessfully
    0.88
     destro
    0.82
    CLASSIFIED
    0.81
     unanimously
    0.76
     showc
    0.75
     pione
    0.74
     initially
    0.74
    Activations Density 0.110%

    No Known Activations