© 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. 4-RES-JB
    11. 1871
    Prev
    Next
    INDEX
    Explanations

    statements reporting information or facts

    oai_token-act-pair · gpt-3.5-turbo

    reporting verbs used in the context of announcements or statements

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

    No Comments

    Negative Logits
    ä½ľ
    -0.70
    aceae
    -0.67
    PLIED
    -0.64
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.62
    ãĥ¯ãĥ³
    -0.61
    bart
    -0.60
    pron
    -0.60
    ctors
    -0.59
     Godd
    -0.59
    ï¸
    -0.59
    POSITIVE LOGITS
     irregularities
    0.73
     links
    0.73
     discrepancies
    0.72
     quoting
    0.68
     indications
    0.65
     timelines
    0.64
     citing
    0.64
     findings
    0.64
     disclosing
    0.64
     filings
    0.63
    Activations Density 0.314%

    No Known Activations