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. 0-RES-JB
    6. 3504
    Prev
    Next
    INDEX
    Explanations

    instances where the word 'presumably' is used in a text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "presumably."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ente
    -0.70
    olutions
    -0.67
    iss
    -0.60
     âĿ
    -0.59
    ento
    -0.58
    urity
    -0.58
    urities
    -0.56
    iece
    -0.55
     success
    -0.54
     &
    -0.54
    POSITIVE LOGITS
     presumably
    3.35
     doubtless
    2.21
     Presumably
    2.07
    umably
    2.07
     evidently
    1.86
     ostensibly
    1.81
     apparently
    1.76
     supposedly
    1.75
     purportedly
    1.60
     undoubtedly
    1.56
    Activations Density 0.009%

    No Known Activations