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. 425
    Prev
    Next
    INDEX
    Explanations

    words related to directions or destinations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "go" in various contexts

    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
    hold
    -0.65
    squ
    -0.62
    aire
    -0.61
     Horus
    -0.60
    scl
    -0.59
    ateurs
    -0.58
    ablo
    -0.57
     inhab
    -0.57
    Naz
    -0.57
     resembled
    -0.56
    POSITIVE LOGITS
    etting
    0.84
    ggle
    0.75
    lems
    0.74
     anyway
    0.73
    !/
    0.73
     downhill
    0.73
     unnoticed
    0.72
     anyways
    0.71
     viral
    0.70
    finding
    0.67
    Activations Density 0.047%

    No Known Activations