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. 8-RES-JB
    6. 71
    Prev
    Next
    INDEX
    Explanations

    computer code snippets

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to safety and emergency situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     microphones
    -0.60
     cameras
    -0.59
     brushes
    -0.57
     camera
    -0.57
    olars
    -0.57
     photographers
    -0.56
     scrub
    -0.55
     brush
    -0.55
     scanner
    -0.55
     marrow
    -0.53
    POSITIVE LOGITS
    '."
    1.06
    )."
    1.06
    .'"
    1.01
    !".
    1.00
    ]."
    0.96
    }"
    0.94
    "'
    0.94
    }.
    0.93
    ").
    0.91
    ".
    0.90
    Activations Density 0.764%

    No Known Activations