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. 24229
    Prev
    Next
    INDEX
    Explanations

    words related to ingestion or consumption, especially of a significant or engulfing nature

    oai_token-act-pair · gpt-3.5-turbo

    terms related to consuming or ingesting

    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
    senal
    -0.71
     psychiat
    -0.70
    romy
    -0.69
     Degree
    -0.67
     diligence
    -0.66
    actionDate
    -0.64
    CTV
    -0.64
    iances
    -0.63
    Weather
    -0.63
    Tech
    -0.62
    POSITIVE LOGITS
    ipes
    0.92
    meat
    0.89
    ritten
    0.86
     chunks
    0.83
     gum
    0.83
     swallow
    0.81
     pork
    0.81
     vines
    0.81
     flakes
    0.80
    tails
    0.79
    Activations Density 0.083%

    No Known Activations