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. 7-RES-JB
    6. 2436
    Prev
    Next
    INDEX
    Explanations

    sequences of steps or instructions

    oai_token-act-pair · gpt-3.5-turbo
    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
    idays
    -0.88
    atform
    -0.84
     Voices
    -0.74
    elaide
    -0.72
    oubted
    -0.71
     claimant
    -0.68
     Journals
    -0.68
    nesty
    -0.66
    ropolitan
    -0.66
    igration
    -0.65
    POSITIVE LOGITS
     routines
    1.21
     technique
    1.09
     tricks
    1.06
     routine
    1.03
     procedure
    1.02
     trick
    0.97
     instructions
    0.97
     manual
    0.97
     techniques
    0.95
     Instruct
    0.95
    Activations Density 1.027%

    No Known Activations