© 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. 10-RES-JB
    11. 1256
    Prev
    Next
    INDEX
    Explanations

    phrases related to the external appearance or first impressions of things

    oai_token-act-pair · gpt-3.5-turbo

    terms related to initial perceptions or appearances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icer
    -0.81
    ashington
    -0.73
    die
    -0.71
    elsen
    -0.69
    rench
    -0.68
    cellaneous
    -0.67
    rop
    -0.66
    arching
    -0.66
    sung
    -0.65
    Joined
    -0.64
    POSITIVE LOGITS
     glance
    1.04
     blush
    0.80
     yes
    0.68
     anyway
    0.64
     it
    0.63
     onlook
    0.63
     LOOK
    0.62
     sounding
    0.62
     seeming
    0.62
     resemb
    0.62
    Activations Density 0.094%

    No Known Activations