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. 5-RES-JB
    6. 21804
    Prev
    Next
    INDEX
    Explanations

    unique and distinctive features or attributes

    oai_token-act-pair · gpt-3.5-turbo

    descriptive terms that emphasize uniqueness or particular traits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ergy
    -0.78
    ©¶æ
    -0.76
    erg
    -0.76
    sent
    -0.73
    married
    -0.72
    jury
    -0.72
    ttp
    -0.71
    ceans
    -0.71
    source
    -0.70
    gres
    -0.69
    POSITIVE LOGITS
    eatures
    0.92
     distinctive
    0.90
    ively
    0.90
     landmarks
    0.88
     likeness
    0.86
     traits
    0.82
     distingu
    0.79
     characteristics
    0.78
    isable
    0.78
     characteristic
    0.77
    Activations Density 0.031%

    No Known Activations