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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 14558
    Prev
    Next
    INDEX
    Explanations

    words related to the internet

    oai_token-act-pair · gpt-3.5-turbo

    references to the internet and its associated concepts

    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
     Clause
    -0.91
     Seal
    -0.81
     Shed
    -0.79
     Electric
    -0.79
     Vander
    -0.79
     Mercy
    -0.76
    士
    -0.76
    NEY
    -0.75
     Bow
    -0.75
     Row
    -0.73
    POSITIVE LOGITS
     cafes
    1.05
     cafe
    0.93
    worms
    0.90
     caf
    0.88
    omnia
    0.85
    community
    0.83
     café
    0.83
    umin
    0.82
    inar
    0.82
    izens
    0.81
    Activations Density 0.041%

    No Known Activations