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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 8077
    Prev
    Next
    INDEX
    Explanations

    words related to specific styles or groups of people

    oai_token-act-pair · gpt-3.5-turbo

    references to hairstyles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wont
    -0.70
     JPM
    -0.66
     barg
    -0.64
     spite
    -0.61
     dumps
    -0.60
     Edge
    -0.60
     capac
    -0.59
     Command
    -0.58
     bulls
    -0.58
     congrat
    -0.58
    POSITIVE LOGITS
    yle
    4.74
    yles
    2.80
    yl
    1.77
    ylan
    1.30
    yd
    1.22
    YL
    1.14
    yne
    1.10
    ylene
    1.08
    yn
    1.05
    yll
    1.04
    Activations Density 0.013%

    No Known Activations