© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 14001
    Prev
    Next
    INDEX
    Explanations

    phrases related to bearing responsibility or negative consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to burdens and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iens
    -0.56
     sten
    -0.56
     contiguous
    -0.56
     diction
    -0.56
     reconnect
    -0.55
     videot
    -0.55
    throp
    -0.54
    cyclopedia
    -0.54
    authorized
    -0.54
    pload
    -0.54
    POSITIVE LOGITS
     blame
    0.81
    Factor
    0.78
     brunt
    0.73
    factor
    0.72
     equation
    0.71
     disadvantage
    0.69
    Brexit
    0.69
     slowdown
    0.66
    Strength
    0.66
    Increased
    0.65
    Activations Density 0.718%

    No Known Activations