Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 1
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental or physical conditions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to environmental conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "conditions"

    oai_token-act-pair · gpt-4-turbo
    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
    sonian
    -0.87
    ãĤ¨ãĥ«
    -0.76
    sub
    -0.69
    enic
    -0.68
     Huff
    -0.66
     Nas
    -0.66
     classmate
    -0.64
     chorus
    -0.63
    umbn
    -0.63
     GN
    -0.62
    POSITIVE LOGITS
     conditions
    1.20
     Conditions
    1.09
    pring
    0.91
     worsened
    0.85
     condition
    0.85
    terday
    0.85
    etting
    0.82
     Condition
    0.81
     deterior
    0.81
    afety
    0.80
    Activations Density 0.012%

    No Known Activations