© 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. 0-RES-JB
    11. 10477
    Prev
    Next
    INDEX
    Explanations

    mentions of words related to craftsmanship or craft, especially when emphasized with higher activation values

    oai_token-act-pair · gpt-3.5-turbo

    references to "raft" or related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Samar
    -0.68
     amygdala
    -0.68
     DOI
    -0.67
     fucking
    -0.65
     Occup
    -0.65
     angels
    -0.65
     LIKE
    -0.64
     behavioral
    -0.63
     Behavioral
    -0.62
     Jordanian
    -0.62
    POSITIVE LOGITS
    raft
    5.18
    rafted
    2.04
    RAFT
    1.66
    rift
    1.33
    rew
    1.19
     graft
    1.16
    draft
    1.12
    raf
    1.08
    uild
    1.03
     Kraft
    1.02
    Activations Density 0.020%

    No Known Activations