© 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. 5202
    Prev
    Next
    INDEX
    Explanations

    phrases related to involvement or participation in an action

    oai_token-act-pair · gpt-3.5-turbo
    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
     DRAG
    -0.92
     Dennis
    -0.87
     Daw
    -0.79
     DL
    -0.79
     Woodward
    -0.77
    çĽ
    -0.77
     Dol
    -0.77
     Dragons
    -0.76
     Dul
    -0.76
    ãĤ¼ãĤ¦ãĤ¹
    -0.75
    POSITIVE LOGITS
    IT
    1.53
    it
    1.48
    iter
    1.37
    ite
    1.30
    ito
    1.28
    ites
    1.26
    iton
    1.23
    itu
    1.22
    ita
    1.20
    its
    1.18
    Activations Density 0.206%

    No Known Activations