© 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. 10-RES-JB
    11. 7007
    Prev
    Next
    INDEX
    Explanations

    adjectives related to negative or serious situations

    oai_token-act-pair · gpt-3.5-turbo

    negative descriptors related to harsh or bleak situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     actionGroup
    -0.72
    afort
    -0.64
    ajo
    -0.63
    ————
    -0.62
     enzyme
    -0.60
     entit
    -0.58
    rase
    -0.56
     Preferred
    -0.56
     Minute
    -0.55
     includ
    -0.55
    POSITIVE LOGITS
    oire
    1.19
    dark
    1.15
    acing
    1.10
    ace
    1.08
    aces
    1.04
    ingly
    0.99
    ly
    0.96
    grim
    0.94
     outlook
    0.93
     prog
    0.88
    Activations Density 0.087%

    No Known Activations