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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 8-RES-JB
    6. 19912
    Prev
    Next
    INDEX
    Explanations

    verbs related to change or influence

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to change and its impact on reality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     towed
    -0.62
    ortment
    -0.60
     maneu
    -0.60
     adapted
    -0.57
     experimented
    -0.56
    iblings
    -0.56
    asionally
    -0.56
    aries
    -0.55
     crept
    -0.55
     assorted
    -0.55
    POSITIVE LOGITS
     anymore
    1.40
     nor
    1.19
    nor
    1.06
     whatsoever
    0.99
     anything
    0.88
     slightest
    0.82
     anybody
    0.81
     any
    0.79
    SPONSORED
    0.77
    galitarian
    0.75
    Activations Density 0.397%

    No Known Activations