Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 58
    Prev
    Next
    INDEX
    Explanations

    names of individuals with the suffix "-ers"

    oai_token-act-pair · gpt-3.5-turbo

    the suffix "ers," indicating people or entities performing actions

    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
    ADRA
    -0.70
     Foss
    -0.67
    URRENT
    -0.63
     numerical
    -0.59
    ¿½
    -0.58
    ĸļ
    -0.56
    nce
    -0.56
     conviction
    -0.56
     Mach
    -0.55
     Downing
    -0.54
    POSITIVE LOGITS
    mith
    1.19
    haw
    1.12
    erker
    1.09
    leeve
    1.07
    ucker
    1.07
    paces
    1.05
    cale
    1.02
    pace
    1.01
    hirt
    1.00
    pec
    0.99
    Activations Density 0.060%

    No Known Activations