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. 3871
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a premise or a condition

    oai_token-act-pair · gpt-3.5-turbo
    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
    okes
    -0.81
    scribe
    -0.80
    rouse
    -0.72
    iner
    -0.72
    inating
    -0.69
    quer
    -0.68
    ade
    -0.67
    queue
    -0.67
    Shop
    -0.66
    imming
    -0.64
    POSITIVE LOGITS
     ample
    0.93
     assurances
    0.88
     hindsight
    0.82
     precedent
    0.82
     how
    0.81
     circumstances
    0.81
     precedence
    0.80
     lack
    0.76
     insufficient
    0.75
     deadlines
    0.74
    Activations Density 0.044%

    No Known Activations