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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9-RES-JB
    6. 14494
    Prev
    Next
    INDEX
    Explanations

    technical specifications or features

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate comprehensiveness or completeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •All the Features!

    No Comments

    Negative Logits
    grad
    -0.72
    Dialogue
    -0.70
    ongo
    -0.70
    chard
    -0.66
    âĵĺ
    -0.65
     aloud
    -0.65
    flation
    -0.65
    ales
    -0.65
    Tweet
    -0.64
    wagon
    -0.64
    POSITIVE LOGITS
     essentials
    1.09
     requisite
    1.07
    isites
    0.96
     necessities
    0.93
     amenities
    0.91
     characteristics
    0.85
     bells
    0.83
     necessary
    0.83
     advantages
    0.82
    essential
    0.81
    Activations Density 0.115%

    No Known Activations