© 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. 4-RES-JB
    11. 5087
    Prev
    Next
    INDEX
    Explanations

    foreign characters or symbols that do not correspond to a specific language but may indicate encoding issues

    oai_token-act-pair · gpt-3.5-turbo

    a specific character or symbol in different contexts

    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
    ufact
    -1.14
    merce
    -0.87
     ethic
    -0.83
     carbohyd
    -0.81
     srf
    -0.79
     synerg
    -0.78
     testim
    -0.77
    raviolet
    -0.73
    psey
    -0.72
     tradem
    -0.72
    POSITIVE LOGITS
    Ī
    1.11
    Ĩ
    1.05
    ãĤĭ
    1.03
    ÃįÃį
    0.94
    ãĥĺ
    0.93
    е
    0.92
    ÑĮ
    0.92
    ĩ
    0.91
    и
    0.91
    à¸
    0.89
    Activations Density 0.009%

    No Known Activations