© 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. 9-RES-JB
    11. 9045
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude

    oai_token-act-pair · gpt-3.5-turbo

    expressions of frustration or strong emotional reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Construction
    -0.69
    arthed
    -0.67
    Officials
    -0.66
    earchers
    -0.65
    ewitness
    -0.64
    sequent
    -0.64
    DAQ
    -0.63
    berus
    -0.63
    Interstitial
    -0.62
     satellite
    -0.62
    POSITIVE LOGITS
     shitty
    0.95
     fucking
    0.95
     fucked
    0.94
     feminism
    0.92
     bullshit
    0.90
     FUCK
    0.87
     Nerd
    0.86
     feminists
    0.85
     condesc
    0.83
     whining
    0.83
    Activations Density 0.922%

    No Known Activations