© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 3586
    Prev
    Next
    INDEX
    Explanations

    descriptions or mentions of things that are pure

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pure" and its various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apter
    -0.85
     prominently
    -0.73
     closest
    -0.72
    è¦ļéĨĴ
    -0.72
     challeng
    -0.72
     notor
    -0.67
    orrow
    -0.66
     Peninsula
    -0.66
    ockets
    -0.65
    agements
    -0.65
    POSITIVE LOGITS
    bred
    1.23
    waters
    1.00
    blood
    0.95
    r
    0.84
    st
    0.81
    blooded
    0.80
    water
    0.78
    pure
    0.76
    hide
    0.76
    ified
    0.73
    Activations Density 0.021%

    No Known Activations