© 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. 3-RES-JB
    11. 15181
    Prev
    Next
    INDEX
    Explanations

    phrases that stand out or emphasize a specific point

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of specific phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.78
    ÄŁ
    -0.76
    hari
    -0.76
     Skydragon
    -0.74
    DERR
    -0.74
    elsen
    -0.73
    ntil
    -0.68
    gur
    -0.66
    gewater
    -0.64
    ©¶æ¥µ
    -0.64
    POSITIVE LOGITS
    phrase
    1.10
     phrase
    1.05
    ology
    1.05
     phrases
    1.00
    terday
    0.90
     uttered
    0.89
    mith
    0.82
    witz
    0.82
    naire
    0.80
    stress
    0.78
    Activations Density 0.008%

    No Known Activations