© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    11. 883
    Prev
    Next
    INDEX
    Explanations

    terms related to specific attributes or descriptions of people or actions, often involving a moral or evaluative component

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations and cultural or political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     «
    -0.80
     realised
    -0.78
     realise
    -0.77
     analyse
    -0.77
     analys
    -0.76
     organis
    -0.76
     organise
    -0.74
    £
    -0.74
     organising
    -0.73
     analysed
    -0.72
    POSITIVE LOGITS
    "—
    1.87
    "
    1.83
    "?
    1.82
    ;"
    1.78
    ";
    1.76
    ":
    1.74
    ."
    1.74
    ,"
    1.73
    "!
    1.65
    "'
    1.59
    Activations Density 0.314%

    No Known Activations