© 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. 13428
    Prev
    Next
    INDEX
    Explanations

    objects related to compliments or positive feedback

    oai_token-act-pair · gpt-3.5-turbo

    expressions of happiness or positive emotions

    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
     pse
    -0.67
    amental
    -0.66
     Inqu
    -0.61
     calculating
    -0.60
    isers
    -0.57
    eem
    -0.56
    EPA
    -0.55
    execute
    -0.55
    uay
    -0.55
    orem
    -0.55
    POSITIVE LOGITS
    agos
    0.80
    clus
    0.78
    Congratulations
    0.65
    clusive
    0.62
     finally
    0.62
    DN
    0.61
    ped
    0.61
     :-)
    0.60
     :)
    0.60
    !]
    0.60
    Activations Density 0.546%

    No Known Activations