© 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. 13958
    Prev
    Next
    INDEX
    Explanations

    phrases related to criticism or negativity

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the sound "sn" in words

    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
    heid
    -0.96
     limited
    -0.63
     ALS
    -0.60
    EMENT
    -0.59
    shire
    -0.58
     respectfully
    -0.58
     Ind
    -0.57
     Britann
    -0.57
     Feld
    -0.55
     tort
    -0.55
    POSITIVE LOGITS
    ugg
    1.29
    uggle
    1.29
    obb
    1.24
    appy
    1.24
    atches
    1.22
    icker
    1.20
    ickers
    1.19
    ipe
    1.19
    ipes
    1.18
    oop
    1.18
    Activations Density 0.014%

    No Known Activations