© 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. 17710
    Prev
    Next
    INDEX
    Explanations

    sports-related terms and possibly names of specific athletes or teams

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to numerical values and measurements

    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
    quartered
    -0.81
    ForgeModLoader
    -0.70
    à¨
    -0.69
     à¨
    -0.64
     è£ıç
    -0.60
    arers
    -0.58
     handwritten
    -0.57
    Documents
    -0.57
    abul
    -0.57
    æĺ
    -0.55
    POSITIVE LOGITS
     ASAP
    1.25
    +.
    1.20
     anyways
    1.09
     depending
    1.03
     if
    1.03
     preferably
    1.02
    +,
    1.02
     (~
    0.99
     unless
    0.97
     tho
    0.97
    Activations Density 0.502%

    No Known Activations