© 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. 22086
    Prev
    Next
    INDEX
    Explanations

    phrases related to returning or coming back

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "back"

    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
    ahime
    -0.67
    anse
    -0.66
    esson
    -0.64
    anto
    -0.63
     Conrad
    -0.59
    JECT
    -0.59
     Rivals
    -0.57
    Ĭ±
    -0.56
     Consent
    -0.56
    Queue
    -0.55
    POSITIVE LOGITS
     home
    0.96
    packs
    0.96
    packing
    0.90
     stronger
    0.86
    stab
    0.83
    tracking
    0.83
     refreshed
    0.82
     HOME
    0.81
     alive
    0.80
    home
    0.75
    Activations Density 0.041%

    No Known Activations