© 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. 9-RES-JB
    11. 23174
    Prev
    Next
    INDEX
    Explanations

    words related to urgency or critical situations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of emotional states and states of need, particularly related to care and assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    authorized
    -0.66
    redit
    -0.62
    lav
    -0.60
    aughed
    -0.60
     itch
    -0.60
     Buckley
    -0.59
    cheat
    -0.58
    aren
    -0.58
     Inher
    -0.57
     Carnival
    -0.56
    POSITIVE LOGITS
     mode
    0.86
     guise
    0.80
     form
    0.79
     manner
    0.74
    shape
    0.73
    bows
    0.72
    ividual
    0.72
     fashion
    0.71
     surroundings
    0.70
     shape
    0.68
    Activations Density 0.182%

    No Known Activations