© 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. 4139
    Prev
    Next
    INDEX
    Explanations

    specific nouns or proper names in a sentence structure

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns and their associated elements within a context

    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
    >>>>
    -0.60
    ©¶æ
    -0.56
    estern
    -0.56
    ishers
    -0.56
     encount
    -0.54
    uckland
    -0.53
     obsolete
    -0.52
    gae
    -0.51
    itutes
    -0.50
    ornia
    -0.49
    POSITIVE LOGITS
     itself
    1.69
     themselves
    1.20
     herself
    1.14
    's
    1.04
     himself
    1.04
     ourselves
    0.86
     oneself
    0.78
    âĢ²
    0.77
     yourself
    0.76
     Himself
    0.76
    Activations Density 0.781%

    No Known Activations