© 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. 9-RES-JB
    11. 2679
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by action verbs

    oai_token-act-pair · gpt-3.5-turbo

    references to risk and security concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ute
    -0.64
    ?????-
    -0.61
    forts
    -0.61
    eal
    -0.58
     Adds
    -0.58
    »Ĵ
    -0.58
    oha
    -0.58
    ixon
    -0.56
     Commando
    -0.56
    Appearances
    -0.55
    POSITIVE LOGITS
     getting
    1.15
     behaving
    1.14
     trying
    1.14
     distributing
    1.14
     stopping
    1.13
     spreading
    1.12
     doing
    1.12
     reacting
    1.12
     slowing
    1.11
     preparing
    1.10
    Activations Density 0.473%

    No Known Activations