© 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. 11-RES-JB
    11. 10096
    Prev
    Next
    INDEX
    Explanations

    Twitter handles

    oai_token-act-pair · gpt-3.5-turbo

    Twitter handles or mentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CDs
    -0.69
     possessions
    -0.64
    abase
    -0.63
     Masquerade
    -0.62
     textbook
    -0.62
     DVDs
    -0.60
     contiguous
    -0.60
     cigarettes
    -0.59
     Fourth
    -0.58
     overtime
    -0.57
    POSITIVE LOGITS
     @
    1.48
    @
    1.24
     twitter
    1.08
     "@
    1.00
    twitter
    0.96
     (@
    0.91
    edin
    0.84
     Follow
    0.82
    iannopoulos
    0.82
     hashtag
    0.81
    Activations Density 0.043%

    No Known Activations