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. 8873
    Prev
    Next
    INDEX
    Explanations

    descriptions or mentions of frank and candid communication

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to honesty and openness in communication

    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
    ammy
    -0.87
    wake
    -0.78
    ÄŁ
    -0.77
    anwhile
    -0.77
    enfranch
    -0.76
    qqa
    -0.74
    BRE
    -0.73
    opes
    -0.71
    FUL
    -0.70
    EFF
    -0.69
    POSITIVE LOGITS
    iasis
    1.02
     candid
    0.91
    ly
    0.89
    ity
    0.85
    ness
    0.82
    iated
    0.80
    iary
    0.79
    furt
    0.77
    Discuss
    0.76
    iator
    0.76
    Activations Density 0.031%

    No Known Activations