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. 1-RES-JB
    6. 10869
    Prev
    Next
    INDEX
    Explanations

    instances of the term "Standard" with varying levels of confidence in the match

    oai_token-act-pair · gpt-3.5-turbo

    references to financial organizations or ratings agencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.79
     rid
    -0.65
    cig
    -0.65
     Khe
    -0.64
     Guerrero
    -0.64
    cific
    -0.62
     Rahul
    -0.62
     Icar
    -0.61
    resent
    -0.61
    gone
    -0.60
    POSITIVE LOGITS
     deviations
    1.00
     deviation
    1.00
     Standard
    0.93
     bearer
    0.79
     Template
    0.79
    arily
    0.78
    é¾įå¥ij士
    0.75
    Standard
    0.75
    ised
    0.74
    emark
    0.73
    Activations Density 0.006%

    No Known Activations