© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 10379
    Prev
    Next
    INDEX
    Explanations

    words related to personal experiences and challenges

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to critical thinking and social awareness

    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
     barring
    -0.67
     theirs
    -0.66
    except
    -0.65
    amera
    -0.64
    ARE
    -0.62
    warning
    -0.62
     alleging
    -0.62
     urging
    -0.60
     supplying
    -0.60
    uploads
    -0.59
    POSITIVE LOGITS
     oneself
    1.34
     yourself
    1.02
     Yourself
    0.93
    azeera
    0.74
     myself
    0.72
    arenthood
    0.71
     shitty
    0.70
     hindsight
    0.66
     entails
    0.65
     mates
    0.63
    Activations Density 0.644%

    No Known Activations