© 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. 3421
    Prev
    Next
    INDEX
    Explanations

    phrases related to visual observation or examination

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the verb "look" and its derivatives in different contexts

    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
    CONCLUS
    -0.75
    è¦ļéĨĴ
    -0.71
    Fact
    -0.70
    accompan
    -0.67
    ãĥĩãĤ£
    -0.67
     Ans
    -0.66
     Recomm
    -0.66
    ãĥ´
    -0.65
     Trad
    -0.64
    LOD
    -0.63
    POSITIVE LOGITS
     disgusted
    1.04
     bored
    1.00
     pissed
    0.98
     horrified
    0.97
     distraught
    0.97
     puzzled
    0.96
     miserable
    0.92
     annoyed
    0.92
     tired
    0.92
     embarrassed
    0.92
    Activations Density 0.052%

    No Known Activations