© 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. 0-RES-JB
    11. 22258
    Prev
    Next
    INDEX
    Explanations

    mentions of the word 'Mod' followed by a number, such as 'Mod 9' or 'Mod 10'

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named "Mod" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĶ°
    -0.92
    taboola
    -0.87
     throats
    -0.79
    pee
    -0.77
     swallow
    -0.74
     crush
    -0.70
     wrestle
    -0.68
     throat
    -0.68
    retty
    -0.68
    hua
    -0.66
    POSITIVE LOGITS
     Mod
    3.71
    Mod
    2.42
     Mods
    2.23
     mod
    2.19
     MOD
    1.99
    mod
    1.95
    Mods
    1.76
    MOD
    1.70
     mods
    1.67
     modification
    1.54
    Activations Density 0.021%

    No Known Activations