Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 2012
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names containing "Cur"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Cur" and its variations in 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
    enger
    -0.71
    ICES
    -0.65
    hetical
    -0.62
    é¾įå
    -0.62
     Universal
    -0.62
     guiActiveUnfocused
    -0.61
    nikov
    -0.61
    ILA
    -0.60
     Unch
    -0.60
     Burgess
    -0.59
    POSITIVE LOGITS
    iosity
    1.28
    iously
    1.26
    tain
    1.24
    rier
    1.13
    few
    1.13
    ricular
    1.12
    rencies
    1.12
    mud
    1.11
    rying
    1.06
    ved
    1.04
    Activations Density 0.033%

    No Known Activations