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. 3-RES-JB
    6. 11877
    Prev
    Next
    INDEX
    Explanations

    statistical values indicating precision or deviation from a mean

    oai_token-act-pair · gpt-3.5-turbo

    statistical data presentation and numerical values related to research

    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
    neys
    -1.00
    uers
    -0.84
    acle
    -0.83
    acles
    -0.83
    igel
    -0.78
    aco
    -0.75
    ocrats
    -0.75
    ierre
    -0.72
    opoulos
    -0.72
    ibel
    -0.71
    POSITIVE LOGITS
    ±
    1.11
     ±
    0.92
     +/-
    0.89
    /+
    0.81
    /-
    0.81
    sin
    0.73
    seconds
    0.73
    (-
    0.69
     crossings
    0.69
    =~=~
    0.68
    Activations Density 0.010%

    No Known Activations