© 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. 2-RES-JB
    11. 898
    Prev
    Next
    INDEX
    Explanations

    words ending in the suffix "ction"

    oai_token-act-pair · gpt-4-turbo

    words or phrases related to actions that are prohibited or restricted

    oai_token-act-pair · gpt-3.5-turbo

    terms related to actions or events, particularly those hinting at restrictions or prohibitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intest
    -0.76
    inav
    -0.71
     unborn
    -0.68
     NX
    -0.68
     Infinite
    -0.65
    ×Ķ
    -0.65
     Schne
    -0.64
    é¾įå
    -0.64
     Lak
    -0.61
     Berkshire
    -0.60
    POSITIVE LOGITS
    ction
    1.05
    naire
    1.03
    ategory
    1.01
    ivated
    0.90
    itious
    0.87
    alled
    0.87
    eers
    0.86
    eering
    0.82
    eer
    0.82
    ation
    0.79
    Activations Density 0.013%

    No Known Activations