© 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. 10-RES-JB
    11. 17509
    Prev
    Next
    INDEX
    Explanations

    capital letters followed by certain patterns that spell out a specific word or name

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'G'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ples
    -0.66
     lapse
    -0.65
    ĸļ
    -0.65
     occupied
    -0.65
     pale
    -0.64
     Hyde
    -0.63
     Mellon
    -0.63
     Aber
    -0.60
     Bam
    -0.60
     retrospect
    -0.59
    POSITIVE LOGITS
    roups
    1.46
    raphic
    1.44
    reetings
    1.36
    reens
    1.31
    entle
    1.30
    uild
    1.27
    rowth
    1.26
    irlfriend
    1.26
    erald
    1.26
    ossip
    1.24
    Activations Density 0.045%

    No Known Activations