© 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. 17774
    Prev
    Next
    INDEX
    Explanations

    phrases related to using various methods or techniques

    oai_token-act-pair · gpt-3.5-turbo

    expressions that refer to various methods or approaches

    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
    oos
    -0.79
    thumbnails
    -0.77
    cart
    -0.70
    wine
    -0.67
    oct
    -0.66
    Kings
    -0.66
    Newsletter
    -0.66
    taboola
    -0.63
    Cart
    -0.61
    ented
    -0.60
    POSITIVE LOGITS
    terday
    1.07
    hift
    0.92
     è£ıè
    0.80
    berra
    0.67
    chwitz
    0.66
    к
    0.66
     means
    0.64
    á½
    0.63
    paces
    0.62
    ername
    0.62
    Activations Density 0.026%

    No Known Activations