© 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. 2721
    Prev
    Next
    INDEX
    Explanations

    names related to social media platforms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Amanda" and related variations

    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
     cardinal
    -0.71
     clustered
    -0.63
    eers
    -0.63
     geography
    -0.63
     comed
    -0.62
     turbulence
    -0.62
     persist
    -0.61
     server
    -0.61
     Mc
    -0.61
     prone
    -0.61
    POSITIVE LOGITS
    Am
    3.71
     Am
    1.58
    Amb
    1.34
    Vi
    1.33
    Ur
    1.29
    am
    1.27
    Ag
    1.26
    Tam
    1.25
    AM
    1.23
    Um
    1.22
    Activations Density 0.021%

    No Known Activations