© 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. 10052
    Prev
    Next
    INDEX
    Explanations

    references to historical events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of assistance or support in various contexts

    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
     Pastebin
    -0.74
    letes
    -0.73
    ã
    -0.72
    tein
    -0.72
     WATCH
    -0.70
     (@
    -0.69
     Repeat
    -0.69
    zbollah
    -0.67
    tenance
    -0.67
     ðŁĺ
    -0.67
    POSITIVE LOGITS
     fledgling
    1.19
     nascent
    1.04
     burgeoning
    0.97
     intrigued
    0.93
     ambitious
    0.93
     budding
    0.85
     postwar
    0.81
     realization
    0.80
     newfound
    0.79
     naïve
    0.79
    Activations Density 1.104%

    No Known Activations