© 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. 4-RES-JB
    11. 13554
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to attainment or achievement

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to attributes or characteristics

    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
    ROM
    -0.77
    Downloadha
    -0.75
     ATI
    -0.75
    HAEL
    -0.74
     Galile
    -0.73
    hyde
    -0.68
     Hearts
    -0.68
    76561
    -0.66
    beard
    -0.66
     Tunisia
    -0.65
    POSITIVE LOGITS
    itudinal
    1.19
    ension
    1.09
    ments
    1.08
    ributes
    1.04
    uning
    1.01
    itudes
    0.99
    itude
    0.97
    inen
    0.97
    ainment
    0.94
    uned
    0.93
    Activations Density 0.007%

    No Known Activations