Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 20888
    Prev
    Next
    INDEX
    Explanations

    phrases containing quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific symbols or characters in the text, particularly unusual ones

    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
     Manhattan
    -0.62
     descending
    -0.62
     glide
    -0.58
     malaria
    -0.58
     naming
    -0.58
     paternal
    -0.57
     antid
    -0.57
     Alc
    -0.57
     Cycl
    -0.57
     Mous
    -0.56
    POSITIVE LOGITS
    ľ
    1.32
    ¬
    1.22
    ¿
    1.22
    ¼
    1.15
    ¦
    1.11
    Ń
    1.11
    ±
    1.11
    ¤
    1.10
    Ķ
    1.09
    º
    1.08
    Activations Density 0.208%

    No Known Activations