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

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 1840
    Prev
    Next
    INDEX
    Explanations

    adjectives and nouns related to emotions and personal qualities, with a focus on negative connotations

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing various forms of "sense."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    annis
    -0.92
    sites
    -0.81
    emort
    -0.67
    solete
    -0.66
    ceed
    -0.66
    morrow
    -0.65
    dule
    -0.64
    onial
    -0.64
    yna
    -0.64
     Videos
    -0.62
    POSITIVE LOGITS
    ively
    0.91
     urgency
    0.82
    omatic
    0.82
    ibility
    0.79
    Msg
    0.78
     compulsion
    0.77
    UAL
    0.75
    ually
    0.74
    lessly
    0.74
    URE
    0.73
    Activations Density 0.024%

    No Known Activations