© 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. 8259
    Prev
    Next
    INDEX
    Explanations

    mentions of negative trends or decreases in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to a decrease or decline in various contexts

    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
    tein
    -0.68
    Sources
    -0.66
    RA
    -0.64
    ":[{"
    -0.64
    Offline
    -0.63
    ramid
    -0.62
    viks
    -0.60
    ocular
    -0.59
    racuse
    -0.58
     Helpful
    -0.58
    POSITIVE LOGITS
    ylon
    0.75
     escal
    0.72
     precip
    0.72
    cember
    0.71
    ous
    0.69
     attrition
    0.68
    wcs
    0.66
     decline
    0.65
     uranium
    0.65
    ingly
    0.65
    Activations Density 0.015%

    No Known Activations