© 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. 2930
    Prev
    Next
    INDEX
    Explanations

    words related to a consecutive sequence or series

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "string" and its variants, as well as related words and concepts

    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
     Congo
    -0.67
     intimid
    -0.67
     tatt
    -0.62
     Colo
    -0.59
     Korea
    -0.58
     indo
    -0.58
    mith
    -0.58
    ync
    -0.58
     Yosemite
    -0.57
     gob
    -0.55
    POSITIVE LOGITS
    ered
    1.48
    erers
    1.45
    erer
    1.43
    ering
    1.36
    ere
    1.35
    erest
    1.34
    entious
    1.19
    rance
    1.19
    els
    1.18
    ence
    1.17
    Activations Density 0.300%

    No Known Activations