© 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. 10-RES-JB
    11. 10565
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication or transmission of information

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "over."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ittal
    -0.86
    OY
    -0.78
    egal
    -0.77
    eria
    -0.69
    ELY
    -0.65
     holder
    -0.64
    OL
    -0.61
    esm
    -0.60
    osure
    -0.60
    og
    -0.59
    POSITIVE LOGITS
    hang
    1.00
    loading
    0.94
    priced
    0.92
    tones
    0.90
     loudspe
    0.90
     lunch
    0.88
    lord
    0.88
    kill
    0.87
    clock
    0.87
     dinner
    0.87
    Activations Density 0.066%

    No Known Activations