© 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. 6-RES-JB
    11. 11593
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific place name

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Nam."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Engels
    -0.71
     understatement
    -0.66
     forecast
    -0.64
     Blackwell
    -0.62
    UID
    -0.62
     extrap
    -0.60
     angels
    -0.60
     devil
    -0.59
     inhib
    -0.58
     subparagraph
    -0.57
    POSITIVE LOGITS
    nam
    1.19
    orously
    1.01
    ned
    0.99
    ovember
    0.98
    eless
    0.98
    essage
    0.96
    ilitary
    0.95
    forth
    0.93
    azing
    0.93
    emon
    0.92
    Activations Density 0.019%

    No Known Activations