© 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. 5139
    Prev
    Next
    INDEX
    Explanations

    mathematical ratios or time-related information, such as time durations or proportions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "PR" related to public relations or promotional content

    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
    lihood
    -0.90
    lings
    -0.76
    mates
    -0.73
     Genesis
    -0.73
    lement
    -0.66
     Resurrection
    -0.66
    forth
    -0.65
    âĵĺ
    -0.65
     filling
    -0.64
    nings
    -0.62
    POSITIVE LOGITS
    ISM
    1.30
    OPER
    1.29
    OF
    1.27
    IME
    1.25
    INC
    1.21
    IOR
    1.18
    IZE
    1.18
    INT
    1.12
    OM
    1.11
    IV
    1.09
    Activations Density 0.018%

    No Known Activations