© 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. 7-RES-JB
    11. 23428
    Prev
    Next
    INDEX
    Explanations

    attributes associated with ethical and moral values

    oai_token-act-pair · gpt-3.5-turbo

    commas in lists of ideas or concepts

    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
    riber
    -0.71
    cients
    -0.71
    cko
    -0.70
    acent
    -0.69
    quet
    -0.69
    upiter
    -0.68
    utor
    -0.68
    ported
    -0.67
    geon
    -0.67
    assed
    -0.67
    POSITIVE LOGITS
     creativity
    1.03
     albeit
    0.99
     heroism
    0.94
     humility
    0.92
     degradation
    0.92
     alienation
    0.89
     intolerance
    0.88
     tolerance
    0.87
     paranoia
    0.86
     bravery
    0.85
    Activations Density 0.355%

    No Known Activations