© 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. 9321
    Prev
    Next
    INDEX
    Explanations

    locations or materials related to natural environments, specifically sand and mud

    oai_token-act-pair · gpt-3.5-turbo

    references to sand and mud

    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
    CTV
    -0.77
     iT
    -0.70
    ISE
    -0.69
    ODUCT
    -0.69
     antioxid
    -0.68
    ostics
    -0.65
     Founders
    -0.64
     unintended
    -0.63
     Compliance
    -0.63
     Hots
    -0.62
    POSITIVE LOGITS
    bags
    1.34
    bag
    1.20
    storms
    1.11
    castle
    1.07
    stone
    1.00
    bars
    0.97
     baths
    0.94
    bath
    0.94
    boxes
    0.93
    pit
    0.93
    Activations Density 0.034%

    No Known Activations