© 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. 3950
    Prev
    Next
    INDEX
    Explanations

    non-English characters and possibly names

    oai_token-act-pair · gpt-3.5-turbo

    characters or symbols frequently used in text

    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
    xus
    -0.95
     misunder
    -0.88
     conduc
    -0.85
     confir
    -0.85
     occas
    -0.83
     surv
    -0.82
     subsequ
    -0.82
     traged
    -0.81
     compr
    -0.80
     obser
    -0.79
    POSITIVE LOGITS
    į
    0.96
    cup
    0.93
    æµ
    0.92
    dash
    0.92
    ı
    0.89
    ãĤĮ
    0.89
    ¤
    0.88
    ł
    0.87
    İ
    0.86
    âĶģ
    0.85
    Activations Density 0.005%

    No Known Activations