© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5462
    Prev
    Next
    INDEX
    Explanations

    numeric values that are the number 1, sometimes accompanied by a hashtag

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number '1' in contexts related to ranking or enumeration

    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
     Lumpur
    -0.83
    awaru
    -0.82
     vel
    -0.72
    usalem
    -0.72
    thinkable
    -0.71
    apon
    -0.67
    ufact
    -0.67
     shopping
    -0.66
     roofs
    -0.66
     doll
    -0.64
    POSITIVE LOGITS
    Password
    1.28
    125
    1.26
    120
    1.21
    000000
    1.13
    128
    1.06
    st
    1.03
    0000000
    1.02
    123
    0.94
    00000000
    0.89
    ½
    0.86
    Activations Density 0.060%

    No Known Activations