© 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. 8-RES-JB
    11. 20318
    Prev
    Next
    INDEX
    Explanations

    references to subscription boxes and giveaways

    oai_token-act-pair · gpt-3.5-turbo

    terms related to subscription boxes and promotional giveaways

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tun
    -0.82
     Kut
    -0.81
     Fin
    -0.80
     Instr
    -0.79
     Fiscal
    -0.78
     Piercing
    -0.78
     Continuous
    -0.77
     Parish
    -0.77
    Footnote
    -0.77
     Rend
    -0.77
    POSITIVE LOGITS
     americ
    1.11
     english
    1.04
     david
    0.93
    clinton
    0.92
     google
    0.90
    city
    0.89
    football
    0.89
    united
    0.88
    music
    0.86
    internet
    0.86
    Activations Density 0.637%

    No Known Activations