© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 20385
    Prev
    Next
    INDEX
    Explanations

    terms related to skateboarding

    oai_token-act-pair · gpt-3.5-turbo

    terms related to skateboarding and waterboarding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eon
    -0.70
     Alc
    -0.68
    EEK
    -0.68
    uild
    -0.65
     temper
    -0.64
     Eld
    -0.64
     Gutenberg
    -0.63
    aila
    -0.63
    ess
    -0.63
     remem
    -0.62
    POSITIVE LOGITS
    boarding
    3.65
    ibur
    1.56
    boards
    0.86
    igon
    0.84
     Showdown
    0.80
     CMS
    0.77
    atography
    0.76
     underworld
    0.74
     vetting
    0.71
    clusion
    0.71
    Activations Density 0.036%

    No Known Activations