© 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. 345
    Prev
    Next
    INDEX
    Explanations

    words containing the repetition of the letter 'b'

    oai_token-act-pair · gpt-4-turbo

    phrases related to a specific topic or brand mentioned as "bb"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "bb" and related variations

    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
     distilled
    -0.72
     fict
    -0.68
    ãĥ´
    -0.67
    choes
    -0.65
    otom
    -0.64
    ãĥĪ
    -0.64
     pessimistic
    -0.63
    paralle
    -0.63
    rified
    -0.62
     metic
    -0.61
    POSITIVE LOGITS
    orld
    1.09
    nn
    0.93
    ::::
    0.93
    zx
    0.90
    bb
    0.89
    ::::::::
    0.83
    obbies
    0.82
    mpeg
    0.81
    iii
    0.81
    qq
    0.80
    Activations Density 0.010%

    No Known Activations