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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16489
    Prev
    Next
    INDEX
    Explanations

    phrases related to imposing authority or stating facts

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the word "who."

    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
    anmar
    -0.81
    ranging
    -0.76
    OME
    -0.67
     guiActiveUnfocused
    -0.64
     newcom
    -0.62
    actionDate
    -0.61
     Moroc
    -0.61
     srfAttach
    -0.59
     Predict
    -0.59
    UNE
    -0.58
    POSITIVE LOGITS
     disagrees
    1.50
     thinks
    1.45
     cares
    1.41
     wants
    1.39
     knows
    1.39
     participates
    1.36
     chooses
    1.36
     believes
    1.34
     hasn
    1.34
     enjoys
    1.33
    Activations Density 0.098%

    No Known Activations