© 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. 2-RES-JB
    11. 1019
    Prev
    Next
    INDEX
    Explanations

    the word "standalone"

    oai_token-act-pair · gpt-4-turbo

    standalone items or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to independent or self-sufficient entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ordon
    -0.70
    onds
    -0.70
    eming
    -0.70
    oras
    -0.69
    giene
    -0.69
    oi
    -0.68
    orio
    -0.68
    Doctors
    -0.68
    laus
    -0.67
    odor
    -0.66
    POSITIVE LOGITS
     standalone
    1.03
    alone
    0.77
    halla
    0.76
     admissions
    0.71
    icated
    0.70
     foray
    0.66
     minded
    0.63
    hetical
    0.63
     editions
    0.62
    BIL
    0.61
    Activations Density 0.010%

    No Known Activations