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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 3369
    Prev
    Next
    INDEX
    Explanations

    instances of the word "right" used in the context of legal entitlement or permission

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to individual rights and entitlements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DAQ
    -0.74
    aco
    -0.70
    models
    -0.67
     Sark
    -0.62
     Gong
    -0.62
    hematic
    -0.62
    oco
    -0.62
    idated
    -0.62
     Coc
    -0.60
    cit
    -0.59
    POSITIVE LOGITS
    eous
    1.02
    wing
    0.86
     wing
    0.84
    Reviewer
    0.80
     flank
    0.76
     fielder
    0.73
     counsel
    0.72
    ario
    0.72
    FUL
    0.71
     conferred
    0.71
    Activations Density 0.050%

    No Known Activations