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. 9-RES-JB
    6. 21849
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions or consequences if something is missing or not done

    oai_token-act-pair · gpt-3.5-turbo

    phrases that start with "Without."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    late
    -0.80
    des
    -0.77
    rolled
    -0.71
    mers
    -0.69
    ÃŃa
    -0.69
    chet
    -0.68
    dry
    -0.67
    mun
    -0.65
    pole
    -0.65
     Appears
    -0.64
    POSITIVE LOGITS
     exception
    1.08
     knowing
    1.01
     mentioning
    1.01
     hesitation
    0.93
     doubt
    0.93
     compromising
    0.86
     realizing
    0.85
     specifying
    0.84
     interruption
    0.83
     adequate
    0.83
    Activations Density 0.043%

    No Known Activations