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. 1-RES-JB
    6. 16970
    Prev
    Next
    INDEX
    Explanations

    dates and events mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "was."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ological
    -0.59
     Millions
    -0.59
     Individuals
    -0.59
     Reports
    -0.57
     Extend
    -0.57
    arming
    -0.57
     Mountains
    -0.57
     invocation
    -0.57
     Individual
    -0.57
     Achieve
    -0.56
    POSITIVE LOGITS
    nt
    1.02
    hers
    1.02
     definitely
    0.95
    hes
    0.82
     certainly
    0.82
    wolf
    0.80
     probably
    0.76
     not
    0.76
    wolves
    0.75
     indeed
    0.74
    Activations Density 0.412%

    No Known Activations