© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 573
    Prev
    Next
    INDEX
    Explanations

    names of train stations

    oai_token-act-pair · gpt-3.5-turbo

    references to various transportation stations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ£
    -0.90
    interstitial
    -0.81
    onies
    -0.74
    IGHTS
    -0.68
     nerv
    -0.68
     Canaver
    -0.67
    mission
    -0.67
     pestic
    -0.67
    cussion
    -0.64
    posium
    -0.63
    POSITIVE LOGITS
     Station
    0.98
    eers
    0.87
    ery
    0.86
    rador
    0.83
     wagon
    0.80
    wreck
    0.78
    wagon
    0.75
    Station
    0.74
    itude
    0.73
    arity
    0.72
    Activations Density 0.021%

    No Known Activations