© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7466
    Prev
    Next
    INDEX
    Explanations

    direct speech attributions

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases indicating attribution or quotation, specifically the word "said" and its variations

    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
    à¦
    -0.78
    otin
    -0.76
    ãĥ¼ãĥ
    -0.76
    ãĥ¡
    -0.71
    tumblr
    -0.70
    \/\/
    -0.68
    1966
    -0.65
    Phys
    -0.64
    à¹
    -0.64
    ãģ®æ
    -0.64
    POSITIVE LOGITS
    hement
    0.79
    ulty
    0.66
     anecd
    0.66
     seq
    0.64
    mington
    0.62
    heit
    0.61
    doms
    0.61
    ieu
    0.60
    orney
    0.60
     ($)
    0.59
    Activations Density 0.269%

    No Known Activations