© 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. 7-RES-JB
    11. 23656
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals or entities with a long history or significant presence in a particular context

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "longtime."

    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
    abad
    -0.94
    illions
    -0.89
    urgy
    -0.87
    ramid
    -0.82
    apo
    -0.82
    ageddon
    -0.82
    hammad
    -0.81
    oÄŁ
    -0.78
    anguage
    -0.78
    atures
    -0.77
    POSITIVE LOGITS
     resident
    0.97
     collaborator
    0.94
     friend
    0.87
     associate
    0.87
     longtime
    0.84
     acquaintance
    0.81
    stay
    0.81
     favorite
    0.78
     favourite
    0.77
     nem
    0.75
    Activations Density 0.032%

    No Known Activations