© 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. 7724
    Prev
    Next
    INDEX
    Explanations

    conjunctions indicating alternative options

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to choices and alternatives

    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
    onday
    -0.64
     Palest
    -0.63
    lets
    -0.60
     Cth
    -0.60
    culated
    -0.60
    english
    -0.59
    inside
    -0.58
    calling
    -0.58
    ARDS
    -0.58
     XIII
    -0.57
    POSITIVE LOGITS
     postpone
    1.28
     abolish
    1.28
     deny
    1.27
     omit
    1.21
     modify
    1.19
     ignore
    1.15
     refute
    1.15
     revoke
    1.12
     cancel
    1.11
     exclude
    1.10
    Activations Density 0.075%

    No Known Activations