© 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. 7-RES-JB
    11. 19005
    Prev
    Next
    INDEX
    Explanations

    complex words or terms containing "aph", with a higher preference for those with "aph" followed by the number 9

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "aph" within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PUT
    -0.76
    nings
    -0.75
    âĸ¬âĸ¬
    -0.74
    swick
    -0.66
     Alps
    -0.64
    PDATE
    -0.63
    LOAD
    -0.62
    ced
    -0.61
     fitting
    -0.61
     Schwarzenegger
    -0.61
    POSITIVE LOGITS
    obia
    1.21
    ysics
    1.21
    ysical
    1.16
    obic
    1.09
    orically
    1.07
    osate
    1.04
    orns
    1.00
    orical
    0.98
    urst
    0.97
    oria
    0.96
    Activations Density 0.026%

    No Known Activations