© 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. 8-RES-JB
    11. 6831
    Prev
    Next
    INDEX
    Explanations

    phrases related to acceptability or lack thereof

    oai_token-act-pair · gpt-3.5-turbo

    terms related to acceptability and unacceptability

    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
    ilant
    -0.91
    planes
    -0.78
    craft
    -0.76
    onso
    -0.76
    ynthesis
    -0.73
    oling
    -0.72
    pelling
    -0.71
    ocket
    -0.71
    cest
    -0.70
    frey
    -0.70
    POSITIVE LOGITS
     behaviour
    0.82
     behavior
    0.81
     srfAttach
    0.81
     deviations
    0.78
     Danger
    0.77
     compromises
    0.77
     standards
    0.74
     norms
    0.73
     defaults
    0.71
     precedent
    0.71
    Activations Density 0.051%

    No Known Activations