© 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. 2-RES-JB
    11. 9363
    Prev
    Next
    INDEX
    Explanations

    phrases related to deep foundational principles or causes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to being established or having a foundational basis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anooga
    -0.76
    tein
    -0.73
     MARK
    -0.68
    emies
    -0.67
    chief
    -0.66
    ctic
    -0.65
    pmwiki
    -0.64
    airs
    -0.63
    nesota
    -0.62
    otos
    -0.62
    POSITIVE LOGITS
     rooted
    0.97
     rooting
    0.75
    kit
    0.71
    SourceFile
    0.69
     embedded
    0.68
     behind
    0.66
     oper
    0.63
     milit
    0.62
     anchored
    0.62
     corrid
    0.61
    Activations Density 0.005%

    No Known Activations