© 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. 5053
    Prev
    Next
    INDEX
    Explanations

    verbs describing actions or plans being carried out

    oai_token-act-pair · gpt-3.5-turbo

    intentions or plans related to development and construction projects

    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
     Explan
    -0.72
    ebin
    -0.72
     Reaction
    -0.71
     Caller
    -0.68
     Akin
    -0.68
    âĺħâĺħ
    -0.67
    ĸļ
    -0.67
    Weak
    -0.67
     Errors
    -0.67
     Comed
    -0.67
    POSITIVE LOGITS
     renov
    1.82
     renovated
    1.60
     redevelop
    1.59
     leased
    1.51
     leases
    1.50
     remod
    1.47
     lease
    1.47
     leasing
    1.45
     renting
    1.43
     refurb
    1.43
    Activations Density 0.422%

    No Known Activations