© 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. 2-RES-JB
    11. 548
    Prev
    Next
    INDEX
    Explanations

    adjectives related to rough or uneven surfaces, especially "rocky"

    oai_token-act-pair · gpt-4-turbo

    adjectives related to terrain characteristics

    oai_token-act-pair · gpt-3.5-turbo

    descriptive adjectives related to difficult or harsh terrain

    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
    abetic
    -0.95
    ©¶æ
    -0.92
    reme
    -0.91
    agents
    -0.90
    endi
    -0.89
    ande
    -0.85
    mas
    -0.84
    ership
    -0.82
    inator
    -0.82
    ulhu
    -0.80
    POSITIVE LOGITS
     rocky
    1.17
     volcanic
    0.99
     shores
    0.89
     paths
    0.88
     seas
    0.87
     uneven
    0.78
     brick
    0.78
     icy
    0.76
     mountainous
    0.76
     eru
    0.75
    Activations Density 0.025%

    No Known Activations