© 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. 4-RES-JB
    11. 3685
    Prev
    Next
    INDEX
    Explanations

    comparisons or contrasts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conditional statements or comparisons

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

    No Comments

    Negative Logits
    reach
    -0.69
    Magn
    -0.64
    ksh
    -0.63
    Kenn
    -0.63
    Image
    -0.62
    Ping
    -0.60
    hess
    -0.58
    Media
    -0.57
    pit
    -0.57
    Via
    -0.56
    POSITIVE LOGITS
    etheless
    0.97
    Ö¼
    0.82
    ï¸ı
    0.70
    ONSORED
    0.70
     guiName
    0.69
    IES
    0.68
     respectively
    0.67
    ymes
    0.66
    ularity
    0.65
    REDACTED
    0.64
    Activations Density 0.650%

    No Known Activations