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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7-RES-JB
    6. 5447
    Prev
    Next
    INDEX
    Explanations

    version numbers, specifically those in the format X.X.X, with an emphasis on the third segment of the version number

    oai_token-act-pair · gpt-3.5-turbo

    decimal points in numerical data or software versions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     affili
    -0.76
     offic
    -0.71
     incarcer
    -0.71
     indo
    -0.69
     deliber
    -0.65
     dishon
    -0.64
     enrol
    -0.64
     calming
    -0.64
     likeness
    -0.63
     giveaway
    -0.63
    POSITIVE LOGITS
    dylib
    1.21
    compatible
    0.92
    jpg
    0.89
    gz
    0.86
    0
    0.86
    jar
    0.86
    zip
    0.85
    fm
    0.82
    amazon
    0.82
    debian
    0.81
    Activations Density 0.036%

    No Known Activations