© 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. 1-RES-JB
    11. 23297
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Level" being associated with different numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to levels in a ranking or categorization system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OPLE
    -0.88
    atell
    -0.72
    ãĥīãĥ©ãĤ´ãĥ³
    -0.72
     wr
    -0.72
     SQU
    -0.68
    umbn
    -0.68
    stros
    -0.68
    ĻĤ
    -0.68
    eln
    -0.66
     retina
    -0.65
    POSITIVE LOGITS
     Level
    1.04
    Level
    1.03
     Levels
    0.85
    level
    0.80
    deck
    0.77
    smith
    0.72
    ership
    0.70
     levels
    0.69
    levels
    0.67
    umes
    0.65
    Activations Density 0.009%

    No Known Activations