© 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. 9-RES-JB
    11. 15648
    Prev
    Next
    INDEX
    Explanations

    negatively perceived words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    expressions of enjoyment or dissatisfaction in reviews

    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
    ewitness
    -0.87
     telephone
    -0.73
    ospons
    -0.72
     Allaah
    -0.69
     ..."
    -0.69
    estern
    -0.68
    upper
    -0.68
    Federal
    -0.68
    fax
    -0.67
    illegal
    -0.66
    POSITIVE LOGITS
     nostalgia
    0.91
     Whedon
    0.89
     pacing
    0.89
     fanbase
    0.87
     indie
    0.84
     tropes
    0.84
     cinematic
    0.84
     genuinely
    0.83
     goddamn
    0.83
     Konami
    0.81
    Activations Density 1.126%

    No Known Activations