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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-RES-JB
    6. 8701
    Prev
    Next
    INDEX
    Explanations

    phrases expressing conditions or requirements

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases indicating necessity or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ran
    -0.57
     triumph
    -0.57
     nods
    -0.56
     various
    -0.56
     nearby
    -0.55
     successful
    -0.54
     recently
    -0.54
     exemplary
    -0.54
    rador
    -0.52
    æµ
    -0.51
    POSITIVE LOGITS
     unless
    3.41
    unless
    2.87
    Unless
    2.13
     Unless
    2.10
     except
    1.89
     until
    1.64
    until
    1.53
    except
    1.52
     lest
    1.49
     regardless
    1.49
    Activations Density 0.013%

    No Known Activations