© 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. 9-RES-JB
    11. 11222
    Prev
    Next
    INDEX
    Explanations

    statements related to global impact or influence

    oai_token-act-pair · gpt-3.5-turbo

    references to societal groups and global issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lopp
    -0.61
    uristic
    -0.57
    reshold
    -0.54
    umn
    -0.54
    á½
    -0.54
    tein
    -0.53
    Reloaded
    -0.52
    ãĤ·ãĥ£
    -0.51
    ikarp
    -0.51
    LOCK
    -0.51
    POSITIVE LOGITS
     alike
    1.96
     respectively
    1.55
     thereof
    1.22
     versa
    1.06
     thereto
    1.00
     accordingly
    0.98
     therein
    0.95
     thereafter
    0.83
     consequ
    0.80
     attRot
    0.79
    Activations Density 0.534%

    No Known Activations