© 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. 10-RES-JB
    11. 24068
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific groups or activities, like religious practices and financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to worship and community involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     interchange
    -0.83
     symmetry
    -0.82
     warp
    -0.78
     unconstitutional
    -0.69
     compressed
    -0.68
     contraception
    -0.65
     sparkling
    -0.64
     repetitive
    -0.64
     contagious
    -0.64
     proportional
    -0.64
    POSITIVE LOGITS
    itives
    1.44
    itors
    1.42
    ateurs
    1.32
    uers
    1.31
    rers
    1.29
    ancers
    1.26
    icians
    1.21
    cers
    1.21
    ators
    1.21
    ents
    1.21
    Activations Density 0.130%

    No Known Activations