© 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
    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. 15358
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a need or intention to achieve a specific outcome or goal

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing strong actions or desires related to progress or change

    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
    athi
    -0.44
     Eater
    -0.43
     Byte
    -0.41
     Springer
    -0.39
     NE
    -0.39
    æ©Ł
    -0.39
    Ö¼
    -0.39
    hra
    -0.38
     Rossi
    -0.38
    Must
    -0.38
    POSITIVE LOGITS
    rue
    0.62
    omever
    0.62
     oneself
    0.53
     uninterrupted
    0.53
    role
    0.49
    morrow
    0.49
     parity
    0.49
     someday
    0.48
    anything
    0.46
     meaningful
    0.46
    Activations Density 2.479%

    No Known Activations