© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 14709
    Prev
    Next
    INDEX
    Explanations

    words related to dogs

    oai_token-act-pair · gpt-3.5-turbo

    mention of dogs or dog-related content

    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
    noon
    -0.72
     cryst
    -0.68
    theless
    -0.65
     toast
    -0.62
     bonds
    -0.61
     millenn
    -0.61
     tradem
    -0.59
     peninsula
    -0.58
     Mub
    -0.56
     witness
    -0.56
    POSITIVE LOGITS
    gers
    1.23
    warts
    1.13
    glers
    1.10
    mire
    1.06
    ga
    0.89
    ogging
    0.88
    gy
    0.87
    ãĤĮ
    0.86
    ogs
    0.84
    ger
    0.83
    Activations Density 0.013%

    No Known Activations