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. 20507
    Prev
    Next
    INDEX
    Explanations

    phrases related to the manner in which actions are carried out

    oai_token-act-pair · gpt-3.5-turbo

    the word "manner" in various contexts

    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
    Dust
    -0.73
    disc
    -0.68
     Vikings
    -0.64
    ropolitan
    -0.64
    hemat
    -0.63
     Patri
    -0.61
    rising
    -0.60
    gaard
    -0.60
    archives
    -0.60
    mers
    -0.59
    POSITIVE LOGITS
    isms
    1.18
     manner
    0.82
    finding
    0.76
    ably
    0.75
    wcsstore
    0.71
    othy
    0.70
    ault
    0.69
    istry
    0.68
     dictated
    0.67
     disposition
    0.67
    Activations Density 0.009%

    No Known Activations