© 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. 8-RES-JB
    11. 1998
    Prev
    Next
    INDEX
    Explanations

    phrases related to cutting something off

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to severing connections or access

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MAT
    -0.79
    FUL
    -0.71
    antine
    -0.69
    WM
    -0.67
    YN
    -0.66
    izarre
    -0.63
    enegger
    -0.63
    ollen
    -0.62
    INGTON
    -0.61
    Writ
    -0.61
    POSITIVE LOGITS
     limbs
    0.85
    pring
    0.84
     valves
    0.76
     disbelief
    0.74
     contact
    0.74
     limb
    0.73
     abruptly
    0.73
    vo
    0.73
    ricular
    0.72
     communication
    0.72
    Activations Density 0.037%

    No Known Activations