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. 9-RES-JB
    6. 19002
    Prev
    Next
    INDEX
    Explanations

    percentage and numerical figures stated in relation to increase or decrease

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and percentage changes in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elf
    -0.70
    £ı
    -0.70
     suffice
    -0.65
    hid
    -0.62
     stre
    -0.60
     darkest
    -0.59
     inexper
    -0.59
     quir
    -0.59
     assignment
    -0.58
     harmless
    -0.57
    POSITIVE LOGITS
    %,
    1.18
    %.
    1.16
    %;
    1.16
    %"
    1.03
    %
    1.01
    dB
    0.97
    fold
    0.96
     percent
    0.95
    bp
    0.90
    %)
    0.90
    Activations Density 0.135%

    No Known Activations