© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 879
    Prev
    Next
    INDEX
    Explanations

    words related to wood or materials, especially when used in construction or as a descriptor of objects

    oai_token-act-pair · gpt-4-turbo

    words related to construction or materials

    oai_token-act-pair · gpt-3.5-turbo

    words related to construction or building materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MJ
    -0.83
    DERR
    -0.79
    GV
    -0.76
    iPhone
    -0.67
    idad
    -0.66
    Ast
    -0.65
    angers
    -0.65
    present
    -0.64
    Aust
    -0.64
     judgment
    -0.63
    POSITIVE LOGITS
     plank
    1.54
    artisan
    0.89
    lass
    0.86
    uten
    0.83
    bean
    0.80
    fish
    0.79
     Shoals
    0.78
    ridge
    0.78
    isher
    0.77
    holder
    0.77
    Activations Density 0.007%

    No Known Activations