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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 6839
    Prev
    Next
    INDEX
    Explanations

    phrases related to search engines and their usage

    oai_token-act-pair · gpt-3.5-turbo

    references to search engines and their functionality

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

    No Comments

    Negative Logits
    enza
    -0.71
    nor
    -0.68
    ufact
    -0.67
    imir
    -0.67
     Alz
    -0.66
    0100
    -0.62
     Cros
    -0.62
    igham
    -0.62
     Wein
    -0.62
    rone
    -0.62
    POSITIVE LOGITS
     SEO
    0.99
     optimization
    0.95
     encyclopedia
    0.84
     craw
    0.78
    browser
    0.78
     analytics
    0.77
    abases
    0.76
     indexed
    0.76
     admins
    0.76
     regex
    0.76
    Activations Density 0.041%

    No Known Activations