© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 23170
    Prev
    Next
    INDEX
    Explanations

    mentions of the word 'ir'

    oai_token-act-pair · gpt-3.5-turbo

    the term "ir" in various contexts, indicating a focus on elements associated with that prefix or substring

    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
     Opera
    -0.69
     Archdemon
    -0.65
     note
    -0.63
     Ou
    -0.62
     Mons
    -0.58
     messenger
    -0.57
    coat
    -0.57
     Fifty
    -0.56
     Hust
    -0.55
    ety
    -0.55
    POSITIVE LOGITS
    resist
    1.25
    rational
    1.21
    respons
    1.16
    regular
    1.15
    idium
    1.14
    responsible
    1.11
    relevant
    1.09
    anian
    1.09
    respective
    1.06
    replace
    1.05
    Activations Density 0.026%

    No Known Activations