© 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. 2-RES-JB
    11. 9366
    Prev
    Next
    INDEX
    Explanations

    phrases or words that emphasize the importance of something within a system or group

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of being essential or necessary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ö¼
    -0.88
    ÃĥÃĤ
    -0.75
    haw
    -0.75
    ander
    -0.73
    thur
    -0.71
    \\\\\\\\
    -0.66
    asta
    -0.66
    ELL
    -0.65
     Pants
    -0.64
    aptic
    -0.64
    POSITIVE LOGITS
     integral
    0.91
    edded
    0.80
     adjunct
    0.76
    ment
    0.72
    isin
    0.71
    ral
    0.70
    ments
    0.70
    teenth
    0.69
    itial
    0.68
    orporated
    0.67
    Activations Density 0.008%

    No Known Activations