© 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. 6-RES-JB
    11. 4446
    Prev
    Next
    INDEX
    Explanations

    mentions of specific minerals

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of minerals

    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
    ILLE
    -0.87
     Ended
    -0.81
    isSpecialOrderable
    -0.72
    Dispatch
    -0.66
    NER
    -0.65
    orld
    -0.64
    Discussion
    -0.64
    ership
    -0.64
    soType
    -0.63
    ":["
    -0.63
    POSITIVE LOGITS
    ogical
    1.23
    istry
    1.04
    ogy
    0.99
     minerals
    0.94
    itions
    0.93
    ically
    0.92
    ritional
    0.90
    ization
    0.86
     mineral
    0.84
    anguage
    0.82
    Activations Density 0.024%

    No Known Activations