© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 9047
    Prev
    Next
    INDEX
    Explanations

    words related to writing or text manipulation

    oai_token-act-pair · gpt-3.5-turbo

    words related to cursive writing and interactions with it

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

    No Comments

    Negative Logits
    Else
    -0.75
     Skydragon
    -0.70
    Ô
    -0.69
     GOODMAN
    -0.69
    Square
    -0.65
    STEM
    -0.65
    Integ
    -0.64
     srfAttach
    -0.64
     Shack
    -0.62
     DISTR
    -0.62
    POSITIVE LOGITS
    ational
    0.92
    ²¾
    0.85
    erate
    0.81
     flav
    0.79
    oured
    0.78
    ĸļ
    0.76
    ouring
    0.76
    keyes
    0.75
    tips
    0.75
    iers
    0.75
    Activations Density 0.021%

    No Known Activations