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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20759
    Prev
    Next
    INDEX
    Explanations

    references to different kinds of departments, units, and experts

    oai_token-act-pair · gpt-3.5-turbo

    themes related to intensity or prominence in diverse contexts

    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
    Iv
    -0.78
    é¾įå
    -0.70
     sidx
    -0.70
     TRUMP
    -0.70
    shown
    -0.68
    ishable
    -0.66
    ãĤ¿
    -0.61
    OTUS
    -0.61
    oother
    -0.61
    theless
    -0.61
    POSITIVE LOGITS
    phia
    0.73
     extraord
    0.72
    manac
    0.71
    undown
    0.70
     Guru
    0.69
     Clive
    0.69
     guru
    0.68
    mos
    0.68
     sects
    0.67
     prolifer
    0.66
    Activations Density 0.754%

    No Known Activations