© 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. 0-RES-JB
    11. 16374
    Prev
    Next
    INDEX
    Explanations

    words related to invoking a strong emotional response or connection

    oai_token-act-pair · gpt-3.5-turbo

    words related to resonance or emotional impact

    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
    azard
    -0.75
    DI
    -0.70
    Hack
    -0.70
    ardless
    -0.68
    dl
    -0.65
    iso
    -0.65
     Shoot
    -0.64
    ft
    -0.63
     Directory
    -0.63
    fold
    -0.62
    POSITIVE LOGITS
     reson
    3.70
     resonance
    3.34
     resonate
    2.98
     Reson
    2.34
     reverber
    2.10
     echoes
    1.42
     ripple
    1.39
     vibr
    1.37
     galvan
    1.28
     perme
    1.27
    Activations Density 0.022%

    No Known Activations