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. 6-RES-JB
    6. 8072
    Prev
    Next
    INDEX
    Explanations

    words related to database operations and information technology

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to various aspects of data and metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rabbit
    -0.69
     groom
    -0.64
     coax
    -0.63
     Emin
    -0.62
     Carrier
    -0.61
     shining
    -0.60
     Sever
    -0.59
     wired
    -0.59
     boil
    -0.59
     Welch
    -0.59
    POSITIVE LOGITS
    tions
    1.00
    lements
    0.93
    tion
    0.92
    uese
    0.91
    ement
    0.89
    mt
    0.83
    ption
    0.83
    oux
    0.82
    ng
    0.80
    ment
    0.80
    Activations Density 0.267%

    No Known Activations