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. 7-RES-JB
    6. 10575
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer systems and software

    oai_token-act-pair · gpt-3.5-turbo

    references to computer systems and software

    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
    urous
    -0.80
    bow
    -0.75
    tein
    -0.73
    onga
    -0.73
    ishable
    -0.71
    uel
    -0.70
    IELD
    -0.66
    æĢ
    -0.66
    istani
    -0.64
    ished
    -0.63
    POSITIVE LOGITS
    atics
    1.09
     integ
    1.00
    atically
    0.98
    wide
    0.91
    atic
    0.90
     architectures
    0.87
    ologies
    0.80
     integration
    0.79
    ctl
    0.78
     systems
    0.77
    Activations Density 0.046%

    No Known Activations