© 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. 21655
    Prev
    Next
    INDEX
    Explanations

    keywords related to the name "Nat"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Nat" and its variations, which likely relate to specific organizations or groups mentioned in the document

    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
     contraceptives
    -0.67
     Peninsula
    -0.67
    wordpress
    -0.66
     Bearing
    -0.66
     bearer
    -0.63
    --------------------------------------------------------
    -0.61
     highs
    -0.61
    STON
    -0.59
     Institution
    -0.58
     derog
    -0.58
    POSITIVE LOGITS
    ivities
    1.11
    acha
    1.10
    ured
    1.02
    asha
    1.02
    anyahu
    1.02
    uro
    0.98
    alia
    0.98
    ivid
    0.97
    ritional
    0.96
    ivas
    0.95
    Activations Density 0.036%

    No Known Activations