© 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. 4-RES-JB
    11. 10897
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "combined with"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "with."

    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
    chat
    -0.75
     Dise
    -0.68
     overrun
    -0.66
    share
    -0.63
    ©¶æ¥µ
    -0.63
    named
    -0.62
    chan
    -0.62
    chief
    -0.62
    span
    -0.61
    zai
    -0.61
    POSITIVE LOGITS
     regard
    0.97
     impunity
    0.93
     regards
    0.88
     respect
    0.83
     vig
    0.75
    trl
    0.71
     precon
    0.66
     superst
    0.62
    ++++++++
    0.60
    ++++++++++++++++
    0.60
    Activations Density 0.079%

    No Known Activations