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. 2-RES-JB
    6. 4612
    Prev
    Next
    INDEX
    Explanations

    phrases related to the abbreviation "IR" or "infrared"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific entity or term referred to as "IR"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xit
    -0.80
    éĹĺ
    -0.71
    ablishment
    -0.70
     Pound
    -0.67
    deck
    -0.66
     Atl
    -0.66
    éŃĶ
    -0.64
    gaard
    -0.64
    ocobo
    -0.63
    Atl
    -0.63
    POSITIVE LOGITS
    WIN
    0.89
    oute
    0.85
    phthal
    0.82
    rared
    0.78
     absorption
    0.76
    WIND
    0.75
    acet
    0.74
    COLOR
    0.73
     cumbers
    0.73
    sighted
    0.73
    Activations Density 0.004%

    No Known Activations