© 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. 2461
    Prev
    Next
    INDEX
    Explanations

    mentions of locations or people with the name "ton"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ton" in various 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
    ptive
    -0.72
    ulative
    -0.71
    PER
    -0.70
    saf
    -0.67
    BILITIES
    -0.66
    ptions
    -0.66
    replace
    -0.61
    rs
    -0.61
    ilitation
    -0.60
    pling
    -0.59
    POSITIVE LOGITS
    nel
    1.10
    ©¶æ¥µ
    0.96
    neau
    0.90
    nian
    0.86
    ium
    0.86
    ville
    0.83
    osaurus
    0.83
    icum
    0.82
    ews
    0.80
    elly
    0.80
    Activations Density 0.089%

    No Known Activations