© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 8546
    Prev
    Next
    INDEX
    Explanations

    terms related to software development and programming concepts, such as encapsulation, abstraction, coupling, and wrappers

    oai_token-act-pair · gpt-3.5-turbo

    terms related to software design concepts and programming structures

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

    No Comments

    Negative Logits
    76561
    -0.82
    å¸
    -0.72
    gall
    -0.71
     Greens
    -0.70
    gear
    -0.69
     patri
    -0.68
    scl
    -0.68
     Hispanic
    -0.66
    女
    -0.66
    980
    -0.66
    POSITIVE LOGITS
     abstraction
    1.15
     backend
    1.07
     runtime
    1.03
     implementations
    1.03
     sandbox
    1.01
     asynchronous
    0.99
     syntax
    0.99
     API
    0.98
     implementation
    0.96
     dependencies
    0.94
    Activations Density 0.268%

    No Known Activations