© 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. 7861
    Prev
    Next
    INDEX
    Explanations

    phrases related to agreement or alignment with a situation or idea

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to societal issues and personal experiences

    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
     Tripoli
    -0.78
     Dob
    -0.71
     Berm
    -0.67
    arp
    -0.66
     Somers
    -0.66
     Caribbean
    -0.65
     charred
    -0.65
     Appalachian
    -0.64
     Berry
    -0.64
     loft
    -0.64
    POSITIVE LOGITS
    âĢ
    1.61
     âĢ
    1.13
    ."
    0.97
    .�
    0.97
    ðŁĺ
    0.90
    .ãĢį
    0.89
    .''
    0.87
    .""
    0.86
    .
    0.86
    .","
    0.84
    Activations Density 0.571%

    No Known Activations