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. 10-RES-JB
    6. 1628
    Prev
    Next
    INDEX
    Explanations

    phrases related to someone returning from a place or event

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "returning from."

    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
    sylv
    -0.76
    lied
    -0.73
    izens
    -0.71
     minded
    -0.71
    CHAT
    -0.69
    eous
    -0.68
    facts
    -0.67
    most
    -0.67
    eyed
    -0.67
    faced
    -0.67
    POSITIVE LOGITS
     vacation
    1.02
     hiber
    1.01
     abroad
    1.01
     exile
    0.99
     whence
    0.99
     captivity
    0.97
     hiatus
    0.91
     overseas
    0.89
     surgery
    0.89
     maternity
    0.88
    Activations Density 0.116%

    No Known Activations