© 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. 8-RES-JB
    11. 9071
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming, such as "parameter", "compiler", "API", and "preprocessor commands"

    oai_token-act-pair · gpt-3.5-turbo

    programming concepts and technical terms related to software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hilton
    -0.73
    waters
    -0.68
    drug
    -0.67
    adult
    -0.67
    morning
    -0.64
    chair
    -0.63
    Cele
    -0.63
    £
    -0.62
    bill
    -0.62
    stre
    -0.61
    POSITIVE LOGITS
     recursive
    1.20
     syntax
    1.18
     runtime
    1.17
     dependencies
    1.17
     implementations
    1.17
     initialization
    1.14
     debugging
    1.14
     deprecated
    1.13
     plugins
    1.11
     API
    1.09
    Activations Density 1.225%

    No Known Activations