© 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. 14232
    Prev
    Next
    INDEX
    Explanations

    instances of the word "nothing"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "nothing" and its variations 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
    grad
    -0.68
    YN
    -0.66
    nikov
    -0.65
    mast
    -0.58
    strength
    -0.58
    trl
    -0.58
    ATIONS
    -0.56
    ophen
    -0.56
    izoph
    -0.55
    ieri
    -0.55
    POSITIVE LOGITS
     else
    1.22
    ness
    1.14
     whatsoever
    1.11
    except
    1.08
     except
    1.00
    nesses
    0.96
     BUT
    0.92
     but
    0.91
    Else
    0.89
    else
    0.88
    Activations Density 0.049%

    No Known Activations