© 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. 1-RES-JB
    11. 8930
    Prev
    Next
    INDEX
    Explanations

    words related to negative or disruptive situations and emotions

    oai_token-act-pair · gpt-3.5-turbo

    words related to a sense of disconnection or disruption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Norn
    -0.76
     Tone
    -0.72
    DragonMagazine
    -0.71
     Pose
    -0.71
     Suit
    -0.70
    OPLE
    -0.67
     Seah
    -0.66
     Goth
    -0.65
     Origins
    -0.65
     Defenders
    -0.65
    POSITIVE LOGITS
    qus
    1.01
    quiet
    0.96
    array
    0.95
    burse
    0.95
    pelling
    0.93
    ruption
    0.91
    rup
    0.91
    affected
    0.90
    itialized
    0.90
    assemb
    0.89
    Activations Density 0.007%

    No Known Activations