© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 4492
    Prev
    Next
    INDEX
    Explanations

    financial market indices

    oai_token-act-pair · gpt-3.5-turbo

    references to various indices used for measurement in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prov
    -0.91
    itely
    -0.73
     reps
    -0.69
    aman
    -0.69
    ously
    -0.67
     phys
    -0.66
     shaman
    -0.66
    ye
    -0.65
    prom
    -0.64
    ily
    -0.63
    POSITIVE LOGITS
     Index
    3.93
     index
    2.11
    Index
    2.07
     indexes
    1.85
     indices
    1.61
    index
    1.60
     Directory
    1.29
     indexed
    1.26
     Rankings
    1.23
     Inventory
    1.17
    Activations Density 0.016%

    No Known Activations