© 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. 13689
    Prev
    Next
    INDEX
    Explanations

    verbs expressing likelihood or preference

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate tendencies or patterns in behavior

    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
    yet
    -0.81
    hello
    -0.74
    bats
    -0.73
    teen
    -0.67
    raq
    -0.66
    ATS
    -0.66
    Ready
    -0.65
    spection
    -0.64
    Valid
    -0.64
    lights
    -0.63
    POSITIVE LOGITS
     prioritize
    1.32
     underestimate
    1.27
     behave
    1.22
     concentrate
    1.20
     specialize
    1.20
     emphasize
    1.19
     prefer
    1.18
     accumulate
    1.17
     overest
    1.16
     rely
    1.16
    Activations Density 0.100%

    No Known Activations