© 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. 15357
    Prev
    Next
    INDEX
    Explanations

    terms related to materials and their conductive properties

    oai_token-act-pair · gpt-3.5-turbo

    terms related to conductivity and materials science

    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
     Leone
    -0.70
     Trayvon
    -0.69
    iHUD
    -0.69
    FK
    -0.68
     Cec
    -0.68
     Priv
    -0.68
    adier
    -0.68
    TIT
    -0.65
    KNOWN
    -0.65
     Kinn
    -0.64
    POSITIVE LOGITS
    onductor
    1.17
    velength
    1.12
    uctor
    1.11
     magnets
    0.96
    ronics
    0.95
     filament
    0.94
    onduct
    0.94
     nanop
    0.93
    istors
    0.88
     alloy
    0.88
    Activations Density 0.076%

    No Known Activations