© 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. 11318
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with "As" and potentially followed by a specific event, observation, or statement

    oai_token-act-pair · gpt-3.5-turbo

    the start of a new sentence or paragraph

    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
    âĸº
    -0.64
    OSE
    -0.63
    /#
    -0.61
     thence
    -0.60
    _-
    -0.60
    ||||
    -0.58
    ··
    -0.57
    —"
    -0.57
    âĢķ
    -0.56
     viz
    -0.55
    POSITIVE LOGITS
    ylum
    1.35
    semb
    1.31
    bestos
    1.30
    phalt
    1.30
    piring
    1.30
    semble
    1.26
    ymm
    1.20
    ynchronous
    1.19
    pects
    1.12
    king
    1.03
    Activations Density 0.060%

    No Known Activations