© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 20920
    Prev
    Next
    INDEX
    Explanations

    adjectives describing negative situations or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating potential consequences or implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngth
    -0.79
    aneers
    -0.65
    ologue
    -0.64
     Commands
    -0.63
    oes
    -0.63
    akers
    -0.60
    anas
    -0.59
    ogenic
    -0.58
     limbs
    -0.58
    vertisements
    -0.58
    POSITIVE LOGITS
    soType
    0.73
    UTC
    0.71
    quickShipAvailable
    0.71
    SourceFile
    0.68
     explan
    0.68
     contradiction
    0.68
    ECA
    0.67
    ECD
    0.66
     incidentally
    0.65
    ï¸
    0.63
    Activations Density 0.450%

    No Known Activations