© 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. 0-RES-JB
    11. 22292
    Prev
    Next
    INDEX
    Explanations

    words related to accruing or accumulating

    oai_token-act-pair · gpt-3.5-turbo

    words related to accuracy or truthfulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mub
    -0.77
     silent
    -0.68
     IOC
    -0.65
     compression
    -0.65
     searches
    -0.64
    gged
    -0.62
     entangled
    -0.62
     intermediary
    -0.59
     dust
    -0.59
     Antar
    -0.59
    POSITIVE LOGITS
    rue
    4.17
    acular
    1.75
    owe
    1.39
    arro
    1.22
    rete
    1.15
    roe
    1.12
    falls
    1.02
    reci
    1.00
    mens
    0.97
    gue
    0.96
    Activations Density 0.052%

    No Known Activations