© 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. 1-RES-JB
    11. 3790
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'through'

    oai_token-act-pair · gpt-3.5-turbo

    the word "through" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     comfort
    -0.71
    igrate
    -0.70
    assic
    -0.66
    OK
    -0.61
     battered
    -0.61
     storm
    -0.61
    ãĤº
    -0.61
    juven
    -0.60
    ipper
    -0.60
     mind
    -0.59
    POSITIVE LOGITS
    through
    1.31
    sonian
    0.97
    edIn
    0.85
    gression
    0.80
    eatures
    0.80
    )=(
    0.78
    ahime
    0.77
    put
    0.77
    \\\\\\\\
    0.76
    rites
    0.75
    Activations Density 0.004%

    No Known Activations