© 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. 4-RES-JB
    11. 2866
    Prev
    Next
    INDEX
    Explanations

    HTML or webpage elements related to styling and links

    oai_token-act-pair · gpt-3.5-turbo

    HTML attributes and values

    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
    ilings
    -0.77
     bilingual
    -0.76
     equivalents
    -0.73
     scattering
    -0.72
     intrins
    -0.72
     hoard
    -0.70
    ADRA
    -0.67
     peripher
    -0.65
    ĵĺ
    -0.64
    SPONSORED
    -0.64
    POSITIVE LOGITS
    true
    1.18
    false
    1.04
    null
    0.94
    "><
    0.92
    external
    0.89
    http
    0.88
    post
    0.88
    ">
    0.88
    hidden
    0.86
    CVE
    0.85
    Activations Density 0.015%

    No Known Activations