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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 3284
    Prev
    Next
    INDEX
    Explanations

    numerical sequences occurring within text

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and statistics

    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
     bearer
    -0.67
    blance
    -0.65
    SPONSORED
    -0.64
    soDeliveryDate
    -0.64
    raltar
    -0.64
    yssey
    -0.60
     faculties
    -0.59
    wagen
    -0.59
    mbudsman
    -0.57
     Preferences
    -0.56
    POSITIVE LOGITS
    igree
    0.68
    pees
    0.63
    apixel
    0.63
    throp
    0.61
     Pwr
    0.61
    itans
    0.61
    oe
    0.59
    irin
    0.58
     msec
    0.57
    oot
    0.57
    Activations Density 0.159%

    No Known Activations