© 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. 6-RES-JB
    11. 12240
    Prev
    Next
    INDEX
    Explanations

    mentions of water or water-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to water and its various properties

    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
    eering
    -0.96
    Reloaded
    -0.81
    ificant
    -0.74
    ures
    -0.74
    Files
    -0.72
    ablishment
    -0.71
    umbn
    -0.71
    eers
    -0.70
    doms
    -0.68
    URES
    -0.67
    POSITIVE LOGITS
    melon
    1.80
    tight
    1.17
    colour
    1.14
    falls
    1.07
    mel
    1.00
    proof
    0.96
     vapor
    0.95
    loo
    0.93
    color
    0.93
    cake
    0.92
    Activations Density 0.031%

    No Known Activations