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. 14058
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and equipment, particularly those involved in information transmission and energy conversion

    oai_token-act-pair · gpt-3.5-turbo

    agent nouns and technical terms related to devices and mechanics

    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
    ÃįÃį
    -0.69
     Kund
    -0.67
    REAM
    -0.65
     Palestin
    -0.64
    buquerque
    -0.63
    MED
    -0.63
    lyak
    -0.63
    SIZE
    -0.62
     waivers
    -0.62
    nn
    -0.62
    POSITIVE LOGITS
    ucker
    0.91
    oute
    0.84
     charms
    0.82
    pole
    0.78
    ipper
    0.77
    hod
    0.76
    adish
    0.76
    operator
    0.75
    wright
    0.74
    poon
    0.73
    Activations Density 0.107%

    No Known Activations