© 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. 2-RES-JB
    11. 7684
    Prev
    Next
    INDEX
    Explanations

    references to specific car models by Tesla

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Tesla vehicle models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.94
    olulu
    -0.94
    èª
    -0.88
    ulhu
    -0.77
    çĦ
    -0.74
    vernment
    -0.74
    OPLE
    -0.73
    die
    -0.72
    aciously
    -0.70
     darkest
    -0.68
    POSITIVE LOGITS
     Model
    1.08
     Models
    0.89
     Mayhem
    0.88
    Model
    0.75
    eer
    0.75
     Operator
    0.75
     Penal
    0.72
     models
    0.70
     Blueprint
    0.70
    urer
    0.69
    Activations Density 0.008%

    No Known Activations