Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 426
    Prev
    Next
    INDEX
    Explanations

    the modal verb "would" indicating the conditional mood

    oai_token-act-pair · gpt-4-turbo

    mentions of legislative actions or proposed bills

    oai_token-act-pair · gpt-3.5-turbo

    the word "would" indicating proposed actions or legislation

    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
    Reporting
    -0.69
    æ³
    -0.68
    Writing
    -0.67
    eyed
    -0.67
    rylic
    -0.65
     Corpus
    -0.62
    Chem
    -0.60
    story
    -0.60
     Kag
    -0.58
    Mal
    -0.58
    POSITIVE LOGITS
     be
    1.06
     surely
    1.00
     doubtless
    0.96
     undoubtedly
    0.94
     inevitably
    0.93
     likely
    0.91
     never
    0.90
    ĸļ
    0.90
     suffice
    0.89
     assume
    0.88
    Activations Density 0.150%

    No Known Activations