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. 146
    Prev
    Next
    INDEX
    Explanations

    conditions or hypothetical situations described with an "if" clause

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements

    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
    emis
    -0.62
    tten
    -0.59
    Born
    -0.58
    assadors
    -0.53
    ANI
    -0.51
    AMY
    -0.51
    atari
    -0.51
    tained
    -0.51
    agnetic
    -0.51
    atro
    -0.50
    POSITIVE LOGITS
     if
    2.91
     unless
    2.02
    if
    1.90
     If
    1.63
     IF
    1.58
    If
    1.58
    unless
    1.54
     whether
    1.40
     whenever
    1.34
     depending
    1.33
    Activations Density 0.102%

    No Known Activations