© 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. 7-RES-JB
    11. 6390
    Prev
    Next
    INDEX
    Explanations

    words related to specific locations or entities such as schools, countries, theaters, and political parties

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to various subjects, such as aviation, education, geography, climate, rewards, anatomy, pet ownership, politics, and entertainment

    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
    llah
    -0.67
    Exception
    -0.65
    venants
    -0.64
    anon
    -0.61
    nown
    -0.59
    pas
    -0.58
    incerity
    -0.58
     sweat
    -0.57
     vicious
    -0.57
     Cheong
    -0.57
    POSITIVE LOGITS
     purposes
    1.39
     sake
    1.24
     upcoming
    0.75
    okers
    0.74
     2019
    0.71
     purpose
    0.70
     viz
    0.67
    umption
    0.66
     2018
    0.65
    ummies
    0.64
    Activations Density 0.632%

    No Known Activations