© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 6317
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or commands that users can perform or carry out in different contexts or platforms

    oai_token-act-pair · gpt-3.5-turbo

    actions related to organizing and managing resources or submissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alion
    -0.68
    etheless
    -0.67
    ãĥ¯
    -0.66
    ngth
    -0.61
    sama
    -0.60
     Archdemon
    -0.59
    CVE
    -0.57
    laughs
    -0.55
    emed
    -0.55
    sorry
    -0.55
    POSITIVE LOGITS
     their
    1.87
    their
    1.80
     themselves
    1.80
     THEIR
    1.60
     Their
    1.51
    Their
    1.42
     theirs
    1.26
    selves
    1.11
     they
    0.95
     selves
    0.92
    Activations Density 0.773%

    No Known Activations