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. 4-RES-JB
    6. 21486
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Raven"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Raven" or "Ravens."

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

    No Comments

    Negative Logits
    olulu
    -0.82
    olate
    -0.82
    ype
    -0.74
     Nicaragua
    -0.74
    opher
    -0.72
    awaru
    -0.71
    oley
    -0.70
    onest
    -0.69
    atchewan
    -0.69
    orea
    -0.68
    POSITIVE LOGITS
    claw
    1.05
     Ravens
    0.90
     Raven
    0.84
    Raven
    0.74
    alties
    0.72
     raven
    0.68
    swick
    0.68
    flex
    0.67
    bat
    0.66
    MIN
    0.66
    Activations Density 0.012%

    No Known Activations