© 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. 3519
    Prev
    Next
    INDEX
    Explanations

    legal terms and permissions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to permissions and allowances

    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
    matched
    -0.69
     collapsing
    -0.69
     collapses
    -0.68
     Opportun
    -0.68
     mitigating
    -0.67
    gone
    -0.66
     uncanny
    -0.66
     doomed
    -0.66
    finder
    -0.65
    forcing
    -0.63
    POSITIVE LOGITS
     possess
    1.18
     participate
    1.17
     practise
    1.08
     operate
    1.07
     partake
    1.03
     enter
    1.02
     wear
    0.99
     attend
    0.98
     use
    0.97
     speak
    0.96
    Activations Density 0.149%

    No Known Activations