© 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. 4-RES-JB
    6. 15995
    Prev
    Next
    INDEX
    Explanations

    names of individuals or teams that are somehow related to various fields or events in a text

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" used in lists or connections between items or people

    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
    natureconservancy
    -0.73
    matter
    -0.71
    :(
    -0.66
    éŃĶ
    -0.66
    physical
    -0.65
    NEY
    -0.64
    visual
    -0.63
    ãĤ·ãĥ£
    -0.62
    Never
    -0.60
    ffect
    -0.60
    POSITIVE LOGITS
     Associates
    0.96
     Sons
    0.94
    rogens
    0.81
    ERSON
    0.75
     thence
    0.75
     others
    0.74
     Testament
    0.70
    rogen
    0.70
     vice
    0.70
    rew
    0.69
    Activations Density 0.390%

    No Known Activations