© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 1631
    Prev
    Next
    INDEX
    Explanations

    phrases indicating activities, thoughts, or thoughts related to an individual's circumstances

    oai_token-act-pair · gpt-3.5-turbo

    specific symbols or characters that indicate player statistics or performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiActiveUnfocused
    -1.02
     disadvant
    -0.80
     discrep
    -0.73
     Palestin
    -0.71
     democracies
    -0.70
     princ
    -0.66
    undown
    -0.66
     adolesc
    -0.64
     converge
    -0.61
     behavi
    -0.61
    POSITIVE LOGITS
    ates
    0.83
    bart
    0.79
    thy
    0.77
    tsy
    0.77
    ¯
    0.76
    felt
    0.76
    phal
    0.76
    said
    0.76
    lich
    0.75
    tarian
    0.75
    Activations Density 0.182%

    No Known Activations