© 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. 4-RES-JB
    11. 14728
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or proper nouns related to the name "Mans" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    the proper noun "Mans" in various contexts

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

    No Comments

    Negative Logits
    ãģĦ
    -0.72
    èª
    -0.71
    é¾įåĸļ士
    -0.70
    WORK
    -0.69
    çĦ
    -0.68
    ties
    -0.68
    vernment
    -0.68
    >>>>>>>>
    -0.68
    BOOK
    -0.68
    tical
    -0.63
    POSITIVE LOGITS
    laughter
    1.18
    pread
    0.96
    hap
    0.93
    plain
    0.87
     Mans
    0.85
    ouri
    0.83
    afi
    0.82
    hare
    0.82
    owe
    0.82
    bridge
    0.82
    Activations Density 0.009%

    No Known Activations