© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 6824
    Prev
    Next
    INDEX
    Explanations

    references to the company "Taco Bell"

    oai_token-act-pair · gpt-3.5-turbo

    references to the brand "Bell"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itives
    -0.77
     wip
    -0.76
    tg
    -0.76
    cffffcc
    -0.71
     Sudan
    -0.69
    ency
    -0.69
    atted
    -0.69
    itiveness
    -0.67
    displayText
    -0.67
    edit
    -0.67
    POSITIVE LOGITS
     Bell
    3.88
    Bell
    3.16
     bell
    1.81
    bell
    1.70
     bells
    1.31
     Bella
    1.28
     Rogers
    1.22
     Belle
    1.22
     Barber
    1.08
     Pett
    1.07
    Activations Density 0.011%

    No Known Activations