© 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. 24036
    Prev
    Next
    INDEX
    Explanations

    references to strong and foundational elements or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to foundational concepts or structural elements

    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
    displayText
    -0.96
    DIT
    -0.93
     Dragonbound
    -0.80
    ãĤ±
    -0.80
    LOAD
    -0.78
    enegger
    -0.77
    cknowled
    -0.75
    ivil
    -0.75
    lyss
    -0.74
    ells
    -0.74
    POSITIVE LOGITS
     pillar
    0.99
     pillars
    0.94
    pillar
    0.74
     Pillar
    0.72
    borough
    0.71
     parach
    0.65
    istas
    0.64
    OPLE
    0.62
     sod
    0.60
     angel
    0.60
    Activations Density 0.019%

    No Known Activations