© 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. 3-RES-JB
    11. 13245
    Prev
    Next
    INDEX
    Explanations

    commonly emphasized or strong descriptive terms

    oai_token-act-pair · gpt-3.5-turbo

    adjectives or phrases highlighting authenticity and clarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andering
    -0.71
    UGE
    -0.68
     obsc
    -0.68
    APH
    -0.66
    anders
    -0.65
    ADS
    -0.64
    OWER
    -0.63
    aimon
    -0.62
    APE
    -0.61
    OTOS
    -0.60
    POSITIVE LOGITS
    ly
    2.38
    LY
    1.40
    liness
    1.35
    lies
    1.32
    lys
    1.27
    edly
    1.15
    theless
    1.07
    fully
    1.06
    ity
    1.03
    liest
    0.98
    Activations Density 0.076%

    No Known Activations