© 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. 23740
    Prev
    Next
    INDEX
    Explanations

    words related to physical obstructions or barriers

    oai_token-act-pair · gpt-3.5-turbo

    terms related to obstruction and structural concepts

    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
     Lans
    -0.70
    butt
    -0.70
    FORE
    -0.69
     allowance
    -0.64
     Hasan
    -0.62
     allowances
    -0.59
    ³³³³
    -0.58
     exha
    -0.58
    BIL
    -0.57
    ITH
    -0.56
    POSITIVE LOGITS
    ions
    1.86
    ors
    1.55
    s
    1.50
    ures
    1.39
    ives
    1.37
    ively
    1.33
    ured
    1.32
    orate
    1.32
    ive
    1.31
    ivity
    1.29
    Activations Density 0.116%

    No Known Activations