© 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 EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 11684
    Prev
    Next
    INDEX
    Explanations

    phrases related to the atmosphere or environment, particularly those suggesting a negative or challenging setting

    oai_token-act-pair · gpt-3.5-turbo

    terms related to environmental and cultural conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arations
    -0.70
    inav
    -0.69
    sight
    -0.68
    opes
    -0.67
     landfall
    -0.67
    haps
    -0.66
     Partial
    -0.65
    notes
    -0.65
     subtract
    -0.64
    gements
    -0.63
    POSITIVE LOGITS
     conducive
    1.12
     atmosphere
    1.10
     perv
    0.94
     fost
    0.92
     environment
    0.89
     perme
    0.82
     Atmosp
    0.80
     clubhouse
    0.76
     backstage
    0.74
     rife
    0.74
    Activations Density 0.220%

    No Known Activations