© 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. 1-RES-JB
    11. 3464
    Prev
    Next
    INDEX
    Explanations

    words related to laws, legal issues, and criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ob"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ivities
    -0.78
    UAL
    -0.78
     waters
    -0.72
     Quan
    -0.68
     Insp
    -0.68
     Flan
    -0.68
    EngineDebug
    -0.67
     Falk
    -0.67
    HAHA
    -0.66
     ORIG
    -0.66
    POSITIVE LOGITS
    lique
    1.34
    ob
    1.23
    ilib
    1.23
    rien
    1.17
    edience
    1.17
    acter
    1.14
    esity
    1.13
    fusc
    1.01
    ols
    1.00
    edient
    1.00
    Activations Density 0.007%

    No Known Activations