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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-RES-JB
    6. 16490
    Prev
    Next
    INDEX
    Explanations

    mentions of changes or transformations in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "changed" that indicate transformation or alteration in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amina
    -0.93
    ç«
    -0.81
    mination
    -0.76
     DRAGON
    -0.72
    APH
    -0.70
    stra
    -0.67
    alty
    -0.66
    á
    -0.66
    ILA
    -0.64
    onz
    -0.64
    POSITIVE LOGITS
    ĸļ
    1.12
     destro
    0.78
     hijacked
    0.77
    changed
    0.77
     radically
    0.75
    ulkan
    0.75
    xual
    0.74
     effected
    0.74
    rawdownloadcloneembedreportprint
    0.73
     drastically
    0.72
    Activations Density 0.015%

    No Known Activations