© 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. 8-RES-JB
    11. 8963
    Prev
    Next
    INDEX
    Explanations

    mentions of legal or criminal sentences

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Sent" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ARDS
    -0.83
    ãģį
    -0.75
    Donnell
    -0.67
    scope
    -0.65
     Toledo
    -0.64
    ARD
    -0.61
    walker
    -0.60
    åĭ
    -0.60
    à¦
    -0.58
     Werner
    -0.57
    POSITIVE LOGITS
    encing
    1.43
    enced
    1.43
    iment
    1.37
    imental
    1.35
    iments
    1.29
    inel
    1.25
    ences
    1.12
    ence
    1.09
    ient
    1.02
    ict
    0.96
    Activations Density 0.042%

    No Known Activations