© 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. 2234
    Prev
    Next
    INDEX
    Explanations

    declarative statements about actions or states

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the state of being or existence

    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
    oras
    -0.67
    ãĥīãĥ©
    -0.66
    SPONSORED
    -0.66
    Shape
    -0.65
    coon
    -0.64
    nant
    -0.64
    ritical
    -0.63
    violence
    -0.62
    rouse
    -0.61
    cair
    -0.60
    POSITIVE LOGITS
     thrilled
    1.24
     pleased
    1.19
     excited
    1.14
     delighted
    1.13
     proud
    1.13
     glad
    1.08
     grateful
    1.06
     stoked
    1.04
     honored
    1.04
     thankful
    1.02
    Activations Density 0.099%

    No Known Activations