© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7523
    Prev
    Next
    INDEX
    Explanations

    adjectives and nouns related to personal characteristics and activities

    oai_token-act-pair · gpt-3.5-turbo

    themes related to freedom and self-reflection

    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
     militias
    -0.58
    iferation
    -0.55
     Constitution
    -0.54
     unconstitutional
    -0.54
     Prosecut
    -0.54
     repressive
    -0.53
    ''.
    -0.53
     Communists
    -0.53
     subsistence
    -0.52
     constitutionally
    -0.52
    POSITIVE LOGITS
     ;)
    0.65
     somew
    0.65
     spoilers
    0.64
     ðŁĻĤ
    0.63
    nesday
    0.63
     :)
    0.62
     disclaimer
    0.61
     themed
    0.60
    canon
    0.58
     haha
    0.58
    Activations Density 1.883%

    No Known Activations