© 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. 10254
    Prev
    Next
    INDEX
    Explanations

    phrases expressing importance or urgency

    oai_token-act-pair · gpt-3.5-turbo

    contractions and variations of the word "is"

    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
    lie
    -0.78
    orem
    -0.72
    %%
    -0.70
    warn
    -0.70
    rose
    -0.69
    neau
    -0.69
    shall
    -0.69
    link
    -0.68
    éĹĺ
    -0.68
    vale
    -0.67
    POSITIVE LOGITS
     exciting
    1.15
     nice
    1.11
     interesting
    1.10
     unfortunate
    1.09
     frustrating
    1.08
     bitters
    1.08
     fascinating
    1.04
     flattering
    1.03
     funny
    1.02
     disappointing
    1.02
    Activations Density 0.152%

    No Known Activations