© 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. 0-RES-JB
    11. 16122
    Prev
    Next
    INDEX
    Explanations

    phrases related to being trustworthy or reliable

    oai_token-act-pair · gpt-3.5-turbo

    terms related to trust and reliability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    plate
    -0.74
    colour
    -0.68
    fare
    -0.66
    bush
    -0.65
    ois
    -0.65
    bath
    -0.63
    ect
    -0.63
    atten
    -0.62
    iga
    -0.62
     Arena
    -0.60
    POSITIVE LOGITS
     trusted
    3.88
     trustworthy
    2.18
     trust
    1.98
     trusting
    1.96
     trusts
    1.91
     respected
    1.73
     entrusted
    1.50
     reputable
    1.48
    trust
    1.47
     reliable
    1.40
    Activations Density 0.013%

    No Known Activations