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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3367
    Prev
    Next
    INDEX
    Explanations

    the name "Max" with varying emphasis

    oai_token-act-pair · gpt-3.5-turbo

    the name "Max" in various contexts within the text

    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
    GROUND
    -0.84
    RECT
    -0.79
    soType
    -0.77
    tale
    -0.73
    ravings
    -0.73
    cipline
    -0.73
    velt
    -0.72
    wark
    -0.72
    keeper
    -0.71
    CHO
    -0.70
    POSITIVE LOGITS
    imus
    1.41
    imil
    1.14
    imize
    1.12
     Payne
    0.99
    imal
    0.97
    ima
    0.91
    itar
    0.90
    imates
    0.83
     Max
    0.82
     Weber
    0.80
    Activations Density 0.007%

    No Known Activations