© 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. 6404
    Prev
    Next
    INDEX
    Explanations

    phrases related to making sure of certain conditions or actions

    oai_token-act-pair · gpt-3.5-turbo

    negations and phrases that suggest restrictions or prohibitions

    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
    utral
    -0.72
    ciation
    -0.69
    ynthesis
    -0.68
    strength
    -0.67
     colleg
    -0.62
    parency
    -0.62
     testament
    -0.61
     admirable
    -0.61
    cour
    -0.61
     rationality
    -0.60
    POSITIVE LOGITS
    mis
    0.95
     misinterpret
    0.95
     accidentally
    0.90
     inadvertently
    0.89
    ombs
    0.83
     misrepresent
    0.83
     ruin
    0.81
     misunderstand
    0.80
     abuses
    0.78
     inadvert
    0.77
    Activations Density 0.193%

    No Known Activations