Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-RES-JB
    6. 12590
    Prev
    Next
    INDEX
    Explanations

    concepts related to theories and cognitive processes

    oai_token-act-pair · gpt-3.5-turbo

    concepts and terms related to learning theory and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    udeb
    -0.74
    Ire
    -0.68
     nightly
    -0.66
     GMT
    -0.65
     Slim
    -0.64
     Commodore
    -0.64
     Leopard
    -0.63
     UAE
    -0.62
    tips
    -0.62
     Dell
    -0.61
    POSITIVE LOGITS
     theory
    1.22
     Theory
    1.22
     causation
    1.09
     theorists
    1.08
     epist
    1.07
    ivism
    1.07
    ilitarian
    1.05
     versus
    1.04
     vs
    1.01
     hypothesis
    1.01
    Activations Density 0.636%

    No Known Activations