© 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. 3-RES-JB
    11. 7016
    Prev
    Next
    INDEX
    Explanations

    phrases related to the word "Solid"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Solid" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulhu
    -0.72
    uberty
    -0.72
     Peninsula
    -0.69
    HAHA
    -0.69
     distracted
    -0.68
    ||||
    -0.67
    efe
    -0.67
    getting
    -0.67
    ãģ§
    -0.66
     spared
    -0.63
    POSITIVE LOGITS
    GoldMagikarp
    1.21
    itary
    1.18
    arity
    1.13
    ified
    1.04
     Solid
    1.04
    Solid
    1.02
    itud
    0.89
    solid
    0.87
    utonium
    0.79
    idad
    0.78
    Activations Density 0.006%

    No Known Activations