© 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. 8-RES-JB
    11. 7674
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "sand"

    oai_token-act-pair · gpt-3.5-turbo

    references to sand or sandy materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aver
    -0.76
     Founders
    -0.66
    Reloaded
    -0.66
    GBT
    -0.66
    ENSE
    -0.65
    ostics
    -0.61
     traged
    -0.61
     posit
    -0.60
     televised
    -0.60
     Madison
    -0.59
    POSITIVE LOGITS
    castle
    1.14
    bag
    1.11
    hill
    1.10
    bags
    1.09
    paper
    1.04
    stone
    0.99
    storms
    0.97
    wic
    0.97
    tro
    0.96
    lot
    0.94
    Activations Density 0.015%

    No Known Activations