© 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. 10-RES-JB
    11. 22211
    Prev
    Next
    INDEX
    Explanations

    references to various financial situations involving money and resources

    oai_token-act-pair · gpt-3.5-turbo

    references to financial resources and their adequacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Topic
    -0.70
    ModLoader
    -0.62
     harshly
    -0.62
     manner
    -0.61
     ACTIONS
    -0.59
    eatures
    -0.59
    WARD
    -0.58
     behalf
    -0.58
     Defendants
    -0.57
     Cosponsors
    -0.57
    POSITIVE LOGITS
     leftover
    1.23
     spare
    1.22
     available
    1.14
     remaining
    1.10
     left
    1.07
     accumulated
    1.01
     strapped
    1.00
     invested
    0.98
     lying
    0.98
     reserves
    0.97
    Activations Density 0.298%

    No Known Activations