© 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 EvalsExportsAPI 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. 14959
    Prev
    Next
    INDEX
    Explanations

    any occurrence of the word "anything"

    oai_token-act-pair · gpt-3.5-turbo

    the word "anything" and its variations in various 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
    estation
    -0.78
    idem
    -0.77
    raid
    -0.74
    rend
    -0.72
    estamp
    -0.69
    ecake
    -0.68
    orously
    -0.68
    rez
    -0.67
    ils
    -0.66
    ruck
    -0.66
    POSITIVE LOGITS
     resembling
    1.15
     else
    1.15
     remotely
    1.08
    Else
    1.00
     Goes
    0.91
     Else
    0.90
     goes
    0.80
     describ
    0.77
     approaching
    0.76
     worthwhile
    0.76
    Activations Density 0.045%

    No Known Activations