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. 2-RES-JB
    6. 9861
    Prev
    Next
    INDEX
    Explanations

    terms related to reputation, particularly instances where it is mentioned in a negative or concerning context

    oai_token-act-pair · gpt-3.5-turbo

    references to reputation and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cise
    -0.84
    vention
    -0.83
    early
    -0.80
    hoe
    -0.77
    eping
    -0.74
    tein
    -0.71
    vent
    -0.70
    rote
    -0.70
    xual
    -0.70
    actic
    -0.68
    POSITIVE LOGITS
     reputation
    1.12
     veter
    1.00
     tremend
    0.85
     certs
    0.84
     tarn
    0.77
     unden
    0.76
     internationally
    0.74
     behavi
    0.73
     notor
    0.72
     abroad
    0.72
    Activations Density 0.011%

    No Known Activations