© 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. 8-RES-JB
    11. 16987
    Prev
    Next
    INDEX
    Explanations

    names of people

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥķãĤ¡
    -0.67
    ãĥ¬
    -0.65
    ģ«
    -0.62
    chest
    -0.62
    κ
    -0.61
    ãĤ¤
    -0.61
    ãĥij
    -0.61
    higher
    -0.60
    ãĤ¤ãĥĪ
    -0.59
    å®
    -0.59
    POSITIVE LOGITS
     testified
    1.07
    enegger
    1.04
     also
    1.01
     admits
    1.00
     acknowledges
    0.99
     meanwhile
    0.97
     apologized
    0.94
     insists
    0.94
    's
    0.92
     denies
    0.91
    Activations Density 0.215%

    No Known Activations