© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 11445
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters and monetary value

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving significant quantities, conditions, or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ecycle
    -0.62
    renheit
    -0.62
    arthed
    -0.60
    senal
    -0.60
    apsed
    -0.59
    Ire
    -0.59
    unci
    -0.58
    zens
    -0.57
    icent
    -0.57
    Reply
    -0.56
    POSITIVE LOGITS
     equals
    1.51
     isn
    1.38
     means
    1.37
     implies
    1.35
     shouldn
    1.31
     signifies
    1.29
     doesn
    1.26
     ain
    1.24
     tends
    1.23
     translates
    1.20
    Activations Density 0.707%

    No Known Activations