© 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. 6-RES-JB
    11. 5597
    Prev
    Next
    INDEX
    Explanations

    phrases expressing desires or aspirations

    oai_token-act-pair · gpt-3.5-turbo

    expressions of desires or aspirations to "be" something specific

    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
    PsyNetMessage
    -0.78
     suffice
    -0.73
     fray
    -0.69
     dispute
    -0.69
     Prescott
    -0.67
     lapse
    -0.64
     glide
    -0.63
     spill
    -0.61
     converge
    -0.60
     Lines
    -0.60
    POSITIVE LOGITS
     able
    1.15
     judged
    0.94
    leeve
    0.92
    ijing
    0.91
    friends
    0.91
    acons
    0.91
    fits
    0.90
    hemoth
    0.88
    heading
    0.86
    league
    0.84
    Activations Density 0.179%

    No Known Activations