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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 15821
    Prev
    Next
    INDEX
    Explanations

    phrases related to proficiency or excellence

    oai_token-act-pair · gpt-3.5-turbo

    the word "well" and its variations, indicating a focus on positive assessments or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omore
    -0.77
    rely
    -0.69
    ggle
    -0.63
    iferation
    -0.60
    ripp
    -0.58
    apixel
    -0.58
    ataka
    -0.58
    inity
    -0.58
    acity
    -0.58
    inous
    -0.57
    POSITIVE LOGITS
    spring
    1.07
     behaved
    0.96
     vers
    0.95
     intention
    0.92
     deserved
    0.92
     suited
    0.92
     documented
    0.89
     acquainted
    0.89
     overdue
    0.89
     underway
    0.88
    Activations Density 0.038%

    No Known Activations