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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4-RES-JB
    6. 17575
    Prev
    Next
    INDEX
    Explanations

    stock market abbreviations such as NASDAQ and NYSE

    oai_token-act-pair · gpt-3.5-turbo

    stock exchange symbols and their related contexts

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

    No Comments

    Negative Logits
    naires
    -0.78
    headers
    -0.70
     Afgh
    -0.64
     payable
    -0.63
    iasis
    -0.60
    response
    -0.60
    hunt
    -0.59
    ffen
    -0.59
    ãĥĥãĥĪ
    -0.59
     surv
    -0.59
    POSITIVE LOGITS
    DAQ
    1.84
    NAS
    1.29
    daq
    1.26
    TY
    1.12
    CAR
    1.08
    emonic
    0.90
    ports
    0.89
    ELY
    0.85
     NAS
    0.85
    emark
    0.82
    Activations Density 0.009%

    No Known Activations