© 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. 8-RES-JB
    11. 3066
    Prev
    Next
    INDEX
    Explanations

    technical or scientific terms and concepts related to different fields like cosmetic products, equipment, materials, statistics, government branches, and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to consumer products and their impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usalem
    -0.77
    MpServer
    -0.61
    must
    -0.61
    "))
    -0.59
    alien
    -0.59
    edo
    -0.57
    Downloadha
    -0.57
    ensable
    -0.56
     }}
    -0.55
    evil
    -0.55
    POSITIVE LOGITS
     wherein
    0.75
     whereby
    0.70
    senal
    0.67
    !:
    0.67
    :[
    0.60
     whose
    0.60
    ï¸
    0.60
     where
    0.59
     onwards
    0.58
     itself
    0.57
    Activations Density 1.071%

    No Known Activations