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. 20768
    Prev
    Next
    INDEX
    Explanations

    verbs related to physical movement or change in direction

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "turn" and its variations in different contexts

    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
    è¦ļéĨĴ
    -0.95
     Crate
    -0.74
    cffff
    -0.68
     constitu
    -0.62
    former
    -0.61
    issance
    -0.58
     Reasons
    -0.58
    é¾įå
    -0.57
    pelling
    -0.56
    DCS
    -0.55
    POSITIVE LOGITS
     around
    1.11
     sideways
    0.96
     beet
    0.95
    around
    0.92
     away
    0.88
     toward
    0.88
     corners
    0.85
     abruptly
    0.84
     heel
    0.83
     towards
    0.82
    Activations Density 0.050%

    No Known Activations