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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 3617
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the United States

    oai_token-act-pair · gpt-3.5-turbo

    references to entities associated with U.S. agencies or officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aside
    -0.69
     bars
    -0.64
     ordering
    -0.62
     assorted
    -0.59
     yellow
    -0.59
     selves
    -0.59
    âĶĢâĶĢ
    -0.58
     corresponding
    -0.58
     supposed
    -0.58
     tackling
    -0.58
    POSITIVE LOGITS
    Conn
    1.18
    PDATED
    1.13
    lyss
    1.11
    nexpected
    1.06
    gly
    1.05
    VA
    1.04
    Mass
    1.03
    psc
    0.99
    CLA
    0.99
    CC
    0.99
    Activations Density 0.047%

    No Known Activations