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. 9-RES-JB
    6. 1183
    Prev
    Next
    INDEX
    Explanations

    offers the prices of products or services

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to age and other statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    20439
    -0.59
    76561
    -0.57
    ©¶æ¥µ
    -0.55
     convict
    -0.54
    cffff
    -0.53
     CNN
    -0.50
     diction
    -0.50
     referen
    -0.50
     Dynam
    -0.50
     anarchism
    -0.49
    POSITIVE LOGITS
    uncle
    0.69
    inki
    0.66
     guiName
    0.60
    Listener
    0.59
     Pharaoh
    0.57
    âĶĢâĶĢâĶĢâĶĢ
    0.57
    radius
    0.56
    pei
    0.56
    ++)
    0.54
    inus
    0.53
    Activations Density 0.079%

    No Known Activations