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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-RES-JB
    6. 22891
    Prev
    Next
    INDEX
    Explanations

    words related to procedures or instructions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a sequence or set of actions

    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
     Mostly
    -0.68
    gyn
    -0.66
     Corpus
    -0.66
    arium
    -0.63
    itute
    -0.63
    fest
    -0.62
     Confederacy
    -0.61
    zeb
    -0.59
     Unlimited
    -0.59
    orter
    -0.59
    POSITIVE LOGITS
     steps
    3.94
     Steps
    2.86
     step
    2.33
    steps
    2.22
     strides
    2.19
    step
    1.85
     Step
    1.74
    Step
    1.64
     stairs
    1.62
     footsteps
    1.61
    Activations Density 0.013%

    No Known Activations