© 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. 3-RES-JB
    11. 14737
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and financial liability

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal liability and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rica
    -0.88
    urations
    -0.85
    rams
    -0.83
    tons
    -0.82
    ergy
    -0.81
    erva
    -0.80
    rique
    -0.80
    etus
    -0.79
    eful
    -0.78
    rient
    -0.77
    POSITIVE LOGITS
     liability
    1.07
     indemn
    0.83
     liabilities
    0.79
     burden
    0.72
     incurred
    0.72
     forgiven
    0.71
     bracket
    0.70
     issuer
    0.69
    BILITY
    0.68
     insurance
    0.66
    Activations Density 0.014%

    No Known Activations