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. 12-RES-JB
    6. 14578
    Prev
    Next
    INDEX
    Explanations

    technical terms related to technology and data processing

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    terms related to technology and its functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     subdivision
    -0.69
    ãĥĩ
    -0.69
    ãĤ®
    -0.68
     è£ıç
    -0.68
    ãĥķãĤ¡
    -0.67
     starters
    -0.65
     Rite
    -0.65
     placeholder
    -0.62
     containment
    -0.61
     DRAG
    -0.61
    POSITIVE LOGITS
    aped
    1.34
    aths
    1.27
    apped
    1.27
    olitical
    1.22
    apping
    1.16
    illion
    1.14
    ape
    1.13
    eport
    1.12
    ocking
    1.10
    aping
    1.10
    Activations Density 0.089%

    No Known Activations