© 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. 9173
    Prev
    Next
    INDEX
    Explanations

    the number "30" followed by either an ordinal indicator or a percentage sign

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number "30" followed by a measurement or time reference

    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
    ramid
    -0.88
    ype
    -0.79
    Reviewer
    -0.78
    ation
    -0.78
    amaru
    -0.77
    atories
    -0.77
    akeru
    -0.76
    ĸļ
    -0.76
    edIn
    -0.76
    liga
    -0.75
    POSITIVE LOGITS
    %"
    0.96
     msec
    0.82
    nm
    0.82
    th
    0.80
     mins
    0.79
     minutes
    0.79
    fps
    0.78
     seconds
    0.76
    30
    0.75
     Seconds
    0.72
    Activations Density 0.033%

    No Known Activations