© 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. 16353
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to credibility

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of credibility

    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
    uv
    -0.93
    frey
    -0.82
    hop
    -0.72
    hib
    -0.72
    berry
    -0.71
    mun
    -0.69
    Shop
    -0.68
    ulton
    -0.68
     Pt
    -0.68
    akings
    -0.67
    POSITIVE LOGITS
     credible
    1.30
     conclud
    0.99
     allegation
    0.86
    redible
    0.86
     unbeliev
    0.85
     referen
    0.85
     trustworthy
    0.84
     adversary
    0.84
     contender
    0.84
     accuser
    0.84
    Activations Density 0.009%

    No Known Activations