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

    Neuronpedia

    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. 11311
    Prev
    Next
    INDEX
    Explanations

    adjectives related to negative characteristics

    oai_token-act-pair · gpt-3.5-turbo

    critical or analytical terms related to judgments and personality traits

    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
     scout
    -0.81
    theless
    -0.80
     elves
    -0.75
     interchange
    -0.73
     sorcerer
    -0.68
     lore
    -0.66
     dwarves
    -0.65
     explorer
    -0.65
     oneself
    -0.64
     mus
    -0.63
    POSITIVE LOGITS
    overed
    1.04
    aches
    1.02
    rupted
    1.00
    cknowled
    0.99
    ared
    0.98
    ots
    0.92
    aped
    0.92
    rupt
    0.92
    erity
    0.91
    omed
    0.90
    Activations Density 0.278%

    No Known Activations