© 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. 1-RES-JB
    11. 3285
    Prev
    Next
    INDEX
    Explanations

    words related to data analysis or statistics

    oai_token-act-pair · gpt-3.5-turbo

    special characters or formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eper
    -0.74
    ragon
    -0.67
    AGE
    -0.67
     bearer
    -0.66
     Prol
    -0.62
     fed
    -0.61
    eryl
    -0.60
    EGIN
    -0.59
    rawdownloadcloneembedreportprint
    -0.59
    iary
    -0.57
    POSITIVE LOGITS
    Ê
    1.32
    ¹
    0.94
    ¼
    0.92
    ¿
    0.91
    ĥ
    0.90
    »
    0.87
    °
    0.86
    ¾
    0.85
    á¹
    0.82
     á
    0.82
    Activations Density 0.002%

    No Known Activations