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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 18731
    Prev
    Next
    INDEX
    Explanations

    phrases indicating time or condition, such as "when," "if," or "once."

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing self-awareness and personal actions

    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
    WER
    -0.72
    oner
    -0.70
    bourg
    -0.68
     Kem
    -0.66
     Ain
    -0.63
    vision
    -0.63
    dor
    -0.63
    far
    -0.63
     âĶľ
    -0.62
     Mong
    -0.61
    POSITIVE LOGITS
    idth
    0.74
     collide
    0.72
    mble
    0.72
    roup
    0.71
     confronted
    0.70
     Chimera
    0.67
    entimes
    0.65
     ceases
    0.65
     otherwise
    0.64
    erva
    0.61
    Activations Density 0.337%

    No Known Activations