© 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. 9-RES-JB
    11. 1764
    Prev
    Next
    INDEX
    Explanations

    phrases related to improvement and progress

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to societal structure and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tained
    -0.58
    ©¶æ
    -0.57
     Upton
    -0.57
    bestos
    -0.57
    uana
    -0.57
     McAuliffe
    -0.57
     Klux
    -0.56
    éĹĺ
    -0.54
    ophers
    -0.54
    addafi
    -0.53
    POSITIVE LOGITS
     everywhere
    1.21
     constantly
    1.16
     accordingly
    1.02
     continually
    0.98
     wherever
    0.95
     EVERY
    0.94
     every
    0.93
     exponentially
    0.93
     unpredict
    0.90
     continuously
    0.88
    Activations Density 1.051%

    No Known Activations