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. 6-RES-JB
    6. 21697
    Prev
    Next
    INDEX
    Explanations

    instances where individuals are stepping down from positions or roles

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "step down"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olver
    -0.65
    ingham
    -0.63
     Tac
    -0.63
    okemon
    -0.63
    MAT
    -0.61
    ãĥ¼ãĥĨãĤ£
    -0.60
    Tang
    -0.60
    Storage
    -0.59
    Catalog
    -0.59
    Supp
    -0.59
    POSITIVE LOGITS
    frog
    0.90
     abruptly
    0.77
    isSpecialOrderable
    0.73
    uting
    0.73
    enary
    0.71
     overseeing
    0.68
    uters
    0.66
     presiding
    0.65
    ocl
    0.65
    untled
    0.65
    Activations Density 0.026%

    No Known Activations