© 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. 10-RES-JB
    11. 6578
    Prev
    Next
    INDEX
    Explanations

    words related to strong interests or fixations, often bordering on unhealthy obsessions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to obsession and fixation

    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
    soType
    -0.71
    stood
    -0.66
    versible
    -0.63
    Medic
    -0.61
    eli
    -0.60
     RIS
    -0.60
     detrim
    -0.59
    comings
    -0.59
    ells
    -0.58
     RNC
    -0.58
    POSITIVE LOGITS
    ishly
    0.93
    iously
    0.84
     obsess
    0.81
     fascination
    0.79
     fixation
    0.76
     fascinated
    0.75
     obsessed
    0.75
     obsession
    0.72
     obs
    0.71
    atically
    0.71
    Activations Density 0.068%

    No Known Activations