Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 2533
    Prev
    Next
    INDEX
    Explanations

    words related to physical body parts, specifically focusing on the neck area

    oai_token-act-pair · gpt-3.5-turbo

    references to neck injuries or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vation
    -0.71
    ãĥ¼ãĥ³
    -0.68
    ãĥĩ
    -0.68
     sunshine
    -0.66
    PLIED
    -0.65
    ðĿ
    -0.64
     intervening
    -0.63
    âĺħâĺħ
    -0.63
    izoph
    -0.62
    abeth
    -0.61
    POSITIVE LOGITS
    lace
    1.29
    neck
    0.98
    erd
    0.93
    beard
    0.89
     Guitar
    0.84
    igans
    0.83
     sweater
    0.82
    bones
    0.81
    er
    0.80
    bone
    0.80
    Activations Density 0.010%

    No Known Activations