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. 6-RES-JB
    6. 11455
    Prev
    Next
    INDEX
    Explanations

    physical characteristics of individuals like hair color and eye color

    oai_token-act-pair · gpt-3.5-turbo

    descriptive attributes related to physical appearances and specifications

    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
    topic
    -0.85
    ModLoader
    -0.84
    uld
    -0.78
    untarily
    -0.77
    agers
    -0.76
    lease
    -0.75
    odor
    -0.75
    nesday
    -0.74
    uesday
    -0.74
    ohm
    -0.74
    POSITIVE LOGITS
     flanked
    0.84
     topped
    0.81
     canopy
    0.81
     protr
    0.81
     boasting
    0.78
     adorned
    0.77
     reminiscent
    0.74
     featuring
    0.73
     incl
    0.72
     crammed
    0.71
    Activations Density 0.380%

    No Known Activations