© 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. 2083
    Prev
    Next
    INDEX
    Explanations

    adjectives related to the thoroughness or quality of a process or work

    oai_token-act-pair · gpt-3.5-turbo

    descriptive adjectives and adverbs that convey a sense of intensity or quality

    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
    anders
    -0.81
    aden
    -0.70
    ploma
    -0.67
    ategory
    -0.66
    iltr
    -0.64
    REL
    -0.64
    APH
    -0.63
    ADS
    -0.63
    verson
    -0.63
    adr
    -0.61
    POSITIVE LOGITS
    ly
    3.26
    LY
    2.11
    fully
    1.43
    lys
    1.41
    liness
    1.41
    lies
    1.37
    ELY
    1.26
    edly
    1.24
    liest
    1.24
    ously
    1.20
    Activations Density 0.261%

    No Known Activations