© 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. 10-RES-JB
    11. 6737
    Prev
    Next
    INDEX
    Explanations

    names of specific geographical locations or people related to these locations

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "Saran," suggesting a focus on names, possibly related to individuals or groups in a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ruary
    -0.90
    ascript
    -0.72
     fict
    -0.66
    nesday
    -0.63
    abase
    -0.61
    rers
    -0.60
    redit
    -0.59
     Cly
    -0.59
     glim
    -0.59
     ashore
    -0.57
    POSITIVE LOGITS
    chev
    0.90
    intel
    0.89
    indu
    0.87
    zeb
    0.86
    yna
    0.86
    agi
    0.82
    kov
    0.81
    ansson
    0.76
    jit
    0.74
    anas
    0.74
    Activations Density 0.122%

    No Known Activations