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. 7-RES-JB
    6. 21979
    Prev
    Next
    INDEX
    Explanations

    phrases containing hypothetical situations or conditional clauses

    oai_token-act-pair · gpt-3.5-turbo

    instances of hypothetical situations or conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inki
    -0.77
    DX
    -0.77
    ©¶æ¥µ
    -0.72
    enos
    -0.67
    often
    -0.66
    ighting
    -0.65
    IDA
    -0.65
    ema
    -0.62
    chin
    -0.62
    Contents
    -0.61
    POSITIVE LOGITS
     beforehand
    0.89
     sooner
    0.85
     hypot
    0.78
     somehow
    0.72
     someday
    0.72
     tomorrow
    0.70
     existed
    0.67
     hadn
    0.64
    essor
    0.64
     somewhere
    0.64
    Activations Density 0.474%

    No Known Activations