© 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. 9-RES-JB
    11. 18157
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences where a statement or observation is being emphasized or highlighted

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "noted."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quer
    -0.88
    imeters
    -0.71
    ãĥİ
    -0.70
     ILCS
    -0.69
    til
    -0.69
    kie
    -0.69
    soever
    -0.69
    agnetic
    -0.69
    ene
    -0.67
    iffe
    -0.66
    POSITIVE LOGITS
     inconsistencies
    1.02
     similarities
    1.01
     how
    0.94
     discrepancies
    0.92
     approving
    0.88
     prominently
    0.83
     irregularities
    0.80
     noting
    0.80
     favorably
    0.79
     differences
    0.78
    Activations Density 0.059%

    No Known Activations