© 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. 6649
    Prev
    Next
    INDEX
    Explanations

    proper abbreviations or acronyms that emphasize the efficiency or classification of an entity

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms related to organizations or systems

    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
     âĢº
    -0.74
    taboola
    -0.67
    imm
    -0.56
    -0.55
     Riley
    -0.53
     Prof
    -0.52
    wh
    -0.52
     HUGE
    -0.52
     CONT
    -0.51
     ç¥ŀ
    -0.50
    POSITIVE LOGITS
    onica
    0.81
    DERR
    0.80
    eers
    0.78
    ERAL
    0.70
    ICA
    0.69
    ilater
    0.68
    eport
    0.66
    ODUCT
    0.66
    HK
    0.65
     inhibitors
    0.64
    Activations Density 0.145%

    No Known Activations