© 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. 16730
    Prev
    Next
    INDEX
    Explanations

    quotes or references to other sources

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to citing sources or references in reporting

    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
    RGB
    -0.83
    quer
    -0.82
    orld
    -0.80
    ould
    -0.78
    visors
    -0.76
    tes
    -0.75
    te
    -0.74
    ire
    -0.74
    carry
    -0.73
    itialized
    -0.72
    POSITIVE LOGITS
     unnamed
    1.00
     sources
    0.93
     unspecified
    0.84
     warnings
    0.83
     factors
    0.83
     examples
    0.81
     motivations
    0.79
     unidentified
    0.78
     motives
    0.77
     inconsistencies
    0.77
    Activations Density 0.038%

    No Known Activations