© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 17202
    Prev
    Next
    INDEX
    Explanations

    phrases related to honesty

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "honest" and its variations, indicating a focus on sincerity and authenticity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lav
    -0.74
    İĭ
    -0.72
    acid
    -0.72
    anus
    -0.72
     Krish
    -0.71
    Ĥİ
    -0.70
    joined
    -0.69
    KEN
    -0.69
    avia
    -0.69
    interrupted
    -0.68
    POSITIVE LOGITS
     broker
    0.89
     honest
    0.88
     honesty
    0.76
     truthful
    0.72
     appraisal
    0.71
     mistake
    0.69
     frank
    0.69
     Honest
    0.68
     deduction
    0.66
     mistakes
    0.66
    Activations Density 0.025%

    No Known Activations