© 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. 3-RES-JB
    11. 6905
    Prev
    Next
    INDEX
    Explanations

    words related to commentary in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    themes related to public health issues and crises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    boro
    -0.73
    iga
    -0.67
    itory
    -0.65
    utic
    -0.65
    utsche
    -0.63
    utics
    -0.63
     diseng
    -0.60
    uly
    -0.60
     honoured
    -0.59
    terday
    -0.59
    POSITIVE LOGITS
    ccording
    1.05
    However
    1.01
    Specifically
    0.94
    Therefore
    0.93
    Sources
    0.92
    Meanwhile
    0.90
    Solution
    0.89
    Both
    0.88
    Their
    0.88
    Until
    0.88
    Activations Density 1.372%

    No Known Activations