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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 16948
    Prev
    Next
    INDEX
    Explanations

    names of locations and people with a 'Kh' sound

    oai_token-act-pair · gpt-3.5-turbo

    names of locations and people, particularly in the context of news related to unrest or conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reincarn
    -0.72
     craw
    -0.68
    rawdownloadcloneembedreportprint
    -0.66
    ãĥł
    -0.63
     synopsis
    -0.61
    LEASE
    -0.61
     pse
    -0.61
    ãĤ¢ãĥ«
    -0.60
     Cav
    -0.59
     ORDER
    -0.58
    POSITIVE LOGITS
     Rouge
    0.88
    obin
    0.84
    hid
    0.84
    ®
    0.79
    enei
    0.79
    oba
    0.79
    nir
    0.77
    stan
    0.76
    abi
    0.76
    «
    0.73
    Activations Density 0.075%

    No Known Activations