© 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. 6-RES-JB
    11. 14513
    Prev
    Next
    INDEX
    Explanations

    words related to negative events or situations that require some form of official intervention or action

    oai_token-act-pair · gpt-3.5-turbo

    situations that involve police intervention and related legal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oros
    -0.62
    natureconservancy
    -0.59
    \",
    -0.59
    yss
    -0.56
    ï¸
    -0.56
    estern
    -0.56
     --------
    -0.54
     ----------------
    -0.54
     differs
    -0.54
    podcast
    -0.53
    POSITIVE LOGITS
     attest
    0.62
     prematurely
    0.58
     unwitting
    0.58
     denouncing
    0.55
     theirs
    0.54
    .).
    0.53
     panicked
    0.53
     nonexistent
    0.53
     nearby
    0.51
     bailout
    0.51
    Activations Density 1.294%

    No Known Activations