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. 3-RES-JB
    6. 14517
    Prev
    Next
    INDEX
    Explanations

    dates in the format Month/Day, likely related to historical events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character '/' in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Syl
    -0.73
     Primordial
    -0.69
     Fletcher
    -0.68
     Angelo
    -0.68
     Obi
    -0.67
    etheless
    -0.67
     creep
    -0.65
    ļéĨĴ
    -0.64
     Friend
    -0.64
     obsc
    -0.64
    POSITIVE LOGITS
    oct
    1.09
    2015
    1.04
    pmwiki
    1.04
    2014
    1.03
    etc
    1.00
    1000
    0.98
    2013
    0.97
    carbon
    0.97
    2017
    0.96
    PUT
    0.95
    Activations Density 0.075%

    No Known Activations