© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 11047
    Prev
    Next
    INDEX
    Explanations

    specific named entities involved in various legal and political events

    oai_token-act-pair · gpt-3.5-turbo

    patterns in legal or judicial terminology

    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
     regener
    -0.74
     reflex
    -0.72
    xual
    -0.72
     ability
    -0.72
     neighb
    -0.71
     mustache
    -0.71
     casc
    -0.69
     nightly
    -0.69
     commissions
    -0.68
     propensity
    -0.68
    POSITIVE LOGITS
    WASHINGTON
    1.53
    SPONSORED
    1.47
    Officials
    1.47
    ADVERTISEMENT
    1.42
    According
    1.42
    Interested
    1.40
    Sources
    1.36
    FILE
    1.34
    Authorities
    1.33
    Shares
    1.32
    Activations Density 0.416%

    No Known Activations