© 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. 7001
    Prev
    Next
    INDEX
    Explanations

    requests for actions or feedback in comments sections or through messages

    oai_token-act-pair · gpt-3.5-turbo

    instructions for user comments or submissions

    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
    leans
    -0.71
    anticipated
    -0.62
    ustomed
    -0.58
    uitous
    -0.56
     centrif
    -0.56
     increasingly
    -0.55
     awoken
    -0.55
     inherited
    -0.55
     luxury
    -0.54
     forced
    -0.53
    POSITIVE LOGITS
     ASAP
    1.01
     preferably
    0.99
     thanking
    0.95
     DOI
    0.91
    @
    0.90
     URL
    0.88
     (@
    0.87
     anonymously
    0.87
    edin
    0.85
    Tweet
    0.85
    Activations Density 0.334%

    No Known Activations