© 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. 16219
    Prev
    Next
    INDEX
    Explanations

    the word "Arc" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific series or franchise related to "Arc."

    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
    tons
    -1.02
    fulness
    -0.77
    Ö¼
    -0.76
    loo
    -0.74
    ging
    -0.72
    liness
    -0.68
    tty
    -0.65
     Nug
    -0.64
    tk
    -0.64
    gie
    -0.63
    POSITIVE LOGITS
    adia
    1.46
    adian
    1.15
    ades
    1.11
    uate
    1.09
    itect
    1.01
    adium
    0.99
    ADE
    0.99
    ana
    0.95
    inia
    0.89
    enary
    0.86
    Activations Density 0.046%

    No Known Activations