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. 10-RES-JB
    6. 17195
    Prev
    Next
    INDEX
    Explanations

    words related to high-end or expensive items or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to high standards or quality in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dull
    -0.74
     Creator
    -0.72
     Anth
    -0.68
     Shell
    -0.66
     XD
    -0.66
     Sawyer
    -0.66
     Hus
    -0.64
     Scripture
    -0.64
     Clyde
    -0.64
     Boe
    -0.63
    POSITIVE LOGITS
    profile
    1.44
    intensity
    1.41
    level
    1.40
    quality
    1.40
    resolution
    1.40
    stakes
    1.40
    risk
    1.39
    ranking
    1.36
    speed
    1.36
    priced
    1.33
    Activations Density 0.036%

    No Known Activations