© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 15339
    Prev
    Next
    INDEX
    Explanations

    terminology related to rocks and geological processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to geology and rock formations

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

    No Comments

    Negative Logits
    --------------------------------------------------------
    -0.74
     Fn
    -0.72
    cert
    -0.67
    OPA
    -0.67
    forward
    -0.67
    ||||
    -0.66
     Ticket
    -0.66
     compulsory
    -0.65
    ï¸
    -0.64
    æ©Ł
    -0.64
    POSITIVE LOGITS
     fragments
    0.92
     habitats
    0.92
     deposits
    0.91
     formations
    0.88
     specimens
    0.87
     caves
    0.86
     lake
    0.85
     mound
    0.84
     footprints
    0.81
     deposited
    0.80
    Activations Density 0.095%

    No Known Activations