© 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. 9527
    Prev
    Next
    INDEX
    Explanations

    mentions of gun-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to the right to bear arms

    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
    urai
    -0.51
     summed
    -0.49
     Variant
    -0.43
     *)
    -0.42
     converted
    -0.42
    trak
    -0.42
     balk
    -0.42
    aily
    -0.41
    anwhile
    -0.40
    theless
    -0.39
    POSITIVE LOGITS
    votes
    0.52
    SPONSORED
    0.51
    advertising
    0.50
    î
    0.49
    Madison
    0.48
    ãĤ¤ãĥĪ
    0.47
    $.
    0.46
    %.
    0.46
    Auth
    0.43
    thood
    0.43
    Activations Density 3.711%

    No Known Activations