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. 6-RES-JB
    6. 21666
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to recognition or acknowledgment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to acknowledgment and validation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hell
    -0.75
    stead
    -0.73
    ffield
    -0.72
    isoft
    -0.72
    quin
    -0.71
    hire
    -0.67
    orld
    -0.64
    ixt
    -0.64
    ieri
    -0.64
    xy
    -0.63
    POSITIVE LOGITS
    ledged
    0.96
    ibly
    0.94
    recogn
    0.84
    ably
    0.81
    ibility
    0.81
    enance
    0.80
    ances
    0.76
     recognition
    0.75
     recognizing
    0.74
     recognize
    0.74
    Activations Density 0.026%

    No Known Activations