© 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. 11-RES-JB
    11. 24147
    Prev
    Next
    INDEX
    Explanations

    terms related to rankings or hierarchy

    oai_token-act-pair · gpt-3.5-turbo

    elements related to competition and collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĥãĤ¯
    -0.69
    Ô
    -0.67
    Sit
    -0.59
    ãģį
    -0.55
    OPER
    -0.54
    \">
    -0.54
    plet
    -0.54
    ãĤª
    -0.53
    erto
    -0.52
    alg
    -0.51
    POSITIVE LOGITS
     ensued
    1.61
     resulted
    1.51
     became
    1.49
     seemed
    1.47
     amounted
    1.46
     gave
    1.43
     culminated
    1.40
     began
    1.39
     flowed
    1.38
     ensured
    1.37
    Activations Density 0.764%

    No Known Activations