Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 20263
    Prev
    Next
    INDEX
    Explanations

    verbs expressing potential or possibility

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases and expectations regarding films and series

    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
     Protective
    -0.70
     Authorization
    -0.67
     Fern
    -0.67
     Wass
    -0.65
     FSA
    -0.64
    ullah
    -0.64
     Anon
    -0.63
     Protection
    -0.63
    private
    -0.62
     Member
    -0.62
    POSITIVE LOGITS
     resonate
    1.24
     inspire
    1.14
     premiered
    1.14
     depict
    1.11
     attract
    1.11
     evoke
    1.10
     feature
    1.10
     satir
    1.10
     aired
    1.08
     offend
    1.07
    Activations Density 0.275%

    No Known Activations