© 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. 16242
    Prev
    Next
    INDEX
    Explanations

    references to organizations or associations, particularly related to society

    oai_token-act-pair · gpt-3.5-turbo

    references related to societal topics or issues

    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
     months
    -0.70
    éĹĺ
    -0.68
     tubes
    -0.65
     Benghazi
    -0.62
     warnings
    -0.62
    士
    -0.62
    ãĥĦ
    -0.61
     misrepresent
    -0.60
     lamb
    -0.59
     Pax
    -0.59
    POSITIVE LOGITS
    iety
    1.41
    isco
    1.28
    Soc
    1.25
    soc
    1.19
    ieties
    1.15
    ietal
    1.03
    ocial
    0.97
    ionics
    0.89
    cer
    0.87
     Soc
    0.86
    Activations Density 0.005%

    No Known Activations