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. 4-RES-JB
    6. 8388
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with the word "Currently"

    oai_token-act-pair · gpt-3.5-turbo

    the word "currently" and its variations indicating present circumstances or states

    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
     Geh
    -0.90
    ped
    -0.76
    ger
    -0.73
    oi
    -0.72
    child
    -0.71
    ription
    -0.69
    bold
    -0.69
    adata
    -0.69
    amins
    -0.68
    alty
    -0.68
    POSITIVE LOGITS
     residing
    0.95
     underway
    0.94
     constituted
    0.88
     housed
    0.87
     employed
    0.86
     exists
    0.85
     represented
    0.85
     slated
    0.84
     listed
    0.84
     existed
    0.84
    Activations Density 0.021%

    No Known Activations