© 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. 1-RES-JB
    11. 9473
    Prev
    Next
    INDEX
    Explanations

    references to the concept of credibility

    oai_token-act-pair · gpt-3.5-turbo

    references to credibility and its perception in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Shop
    -0.78
    hib
    -0.77
    sets
    -0.75
    hire
    -0.72
    mare
    -0.71
    EMS
    -0.68
     Sparrow
    -0.68
    xon
    -0.68
    uv
    -0.67
    lyss
    -0.66
    POSITIVE LOGITS
     credibility
    1.37
     legitimacy
    1.13
     credentials
    0.99
     tremend
    0.95
     validity
    0.86
     guiActiveUn
    0.86
     cred
    0.84
    ibly
    0.83
     clout
    0.83
     authenticity
    0.82
    Activations Density 0.008%

    No Known Activations