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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 11879
    Prev
    Next
    INDEX
    Explanations

    asymmetric terms or phrases

    oai_token-act-pair · gpt-3.5-turbo

    terms related to asymmetry and symmetry in biological and physical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Footnote
    -0.76
     Dough
    -0.72
    Assembly
    -0.69
    Interstitial
    -0.69
     Fame
    -0.67
    â̦â̦â̦â̦â̦â̦â̦â̦
    -0.66
    AMI
    -0.66
     Undead
    -0.66
     ado
    -0.65
     Muse
    -0.65
    POSITIVE LOGITS
    etrical
    1.83
    etric
    1.69
    etr
    1.38
    etry
    1.21
    ymm
    1.03
     symm
    1.02
    yip
    1.00
     asymm
    0.99
    eties
    0.93
    ethy
    0.93
    Activations Density 0.021%

    No Known Activations