© 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. 499
    Prev
    Next
    INDEX
    Explanations

    words related to information technology and devices

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations and acronyms related to technology and decision-making

    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
     optionally
    -0.66
    ishes
    -0.66
    odder
    -0.60
     CNS
    -0.56
     devoid
    -0.54
     Whats
    -0.53
    ãħĭ
    -0.53
     Frog
    -0.52
     RU
    -0.52
     spawning
    -0.52
    POSITIVE LOGITS
    umerable
    0.89
    é¾įå
    0.73
    acan
    0.73
    æ©
    0.70
    idis
    0.68
    annis
    0.68
    etus
    0.68
    gat
    0.67
    ãĤ¨ãĥ«
    0.66
    agree
    0.66
    Activations Density 0.125%

    No Known Activations