© 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. 7-RES-JB
    11. 8641
    Prev
    Next
    INDEX
    Explanations

    the word "These" at the beginning of sentences

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "These [number]" indicating the introduction of points or examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zzle
    -0.79
    ë
    -0.69
    formance
    -0.68
    ISON
    -0.68
    opus
    -0.68
    their
    -0.66
    achus
    -0.65
    party
    -0.64
    âģ
    -0.64
    onis
    -0.64
    POSITIVE LOGITS
     findings
    0.96
     results
    0.92
     factors
    0.90
     facts
    0.89
     latter
    0.89
     kinds
    0.87
     discrepancies
    0.86
     changes
    0.85
     considerations
    0.84
     truths
    0.83
    Activations Density 0.094%

    No Known Activations