© 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. 0-RES-JB
    11. 8075
    Prev
    Next
    INDEX
    Explanations

    instances of the number 20

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number "20" followed by "th" or "9"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Embedding Space Digit Features

    No Comments

    Negative Logits
    iliated
    -0.70
    ouse
    -0.66
    essors
    -0.66
    jri
    -0.65
    adata
    -0.65
    Pg
    -0.63
    ctl
    -0.61
    backer
    -0.60
     rul
    -0.60
    iliate
    -0.60
    POSITIVE LOGITS
     20
    2.88
     19
    2.12
     30
    2.11
     25
    2.11
     21
    2.11
     40
    2.04
     22
    2.02
     15
    1.96
     50
    1.86
     23
    1.84
    Activations Density 0.029%

    No Known Activations