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. 3-RES-JB
    6. 2557
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific organization or event called "Apostacon"

    oai_token-act-pair · gpt-3.5-turbo

    the term "acon" and its variations in different contexts

    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
     Hegel
    -0.73
    ĸļ
    -0.67
    WHERE
    -0.65
     pageant
    -0.62
     payoff
    -0.62
    lihood
    -0.60
     Fiction
    -0.59
     proble
    -0.59
     haste
    -0.57
     reciproc
    -0.56
    POSITIVE LOGITS
    nect
    1.27
    icum
    1.01
    acon
    0.94
    iso
    0.92
    ople
    0.91
    stant
    0.89
    cil
    0.87
    ervative
    0.86
    itans
    0.86
    adel
    0.85
    Activations Density 0.010%

    No Known Activations