© 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. 13717
    Prev
    Next
    INDEX
    Explanations

    negative statements or self-criticism

    oai_token-act-pair · gpt-3.5-turbo

    negations

    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
     simultane
    -0.67
     mathemat
    -0.65
     bicy
    -0.62
     CY
    -0.61
     ascending
    -0.60
     blanket
    -0.60
     retirees
    -0.59
     networking
    -0.58
     Scarlet
    -0.58
     ANGEL
    -0.57
    POSITIVE LOGITS
    t
    1.53
    tion
    1.21
    tions
    1.16
    ti
    1.12
    tis
    1.10
    tre
    1.07
    tar
    1.06
    nt
    1.04
    td
    1.04
    tu
    1.02
    Activations Density 0.150%

    No Known Activations