Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 15869
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions and activities

    oai_token-act-pair · gpt-3.5-turbo

    verbs associated with legal, political, and organizational actions

    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
     [/
    -0.82
    ãĢİ
    -0.81
    о
    -0.76
    this
    -0.75
    edi
    -0.75
    soType
    -0.72
    _.
    -0.70
    ****
    -0.69
    adh
    -0.69
    ______
    -0.69
    POSITIVE LOGITS
     countless
    1.39
     dozens
    1.38
     numerous
    1.35
     innumerable
    1.34
     myriad
    1.31
     hundreds
    1.17
     thousands
    1.08
     sporadic
    1.08
     plenty
    1.03
     frequent
    1.03
    Activations Density 0.489%

    No Known Activations