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. 3-RES-JB
    6. 22440
    Prev
    Next
    INDEX
    Explanations

    words related to organizing, allocating, and coordinating resources

    oai_token-act-pair · gpt-3.5-turbo

    terms related to organization and resource allocation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    founded
    -0.63
    ammy
    -0.63
     afore
    -0.58
    ixed
    -0.55
    ple
    -0.54
    founder
    -0.53
     Bagg
    -0.53
    aver
    -0.53
     pleading
    -0.53
     brow
    -0.52
    POSITIVE LOGITS
    ments
    1.11
    ings
    0.88
    INGS
    0.84
    able
    0.84
    ively
    0.79
    odox
    0.78
    itures
    0.78
    ables
    0.75
    uate
    0.74
    eston
    0.74
    Activations Density 0.415%

    No Known Activations