© 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. 6223
    Prev
    Next
    INDEX
    Explanations

    phrases indicating recommendations or suggestions

    oai_token-act-pair · gpt-3.5-turbo

    suggestions or recommendations

    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
    ELD
    -0.87
    pires
    -0.73
    binding
    -0.66
    Fra
    -0.63
    ONSORED
    -0.59
     Khalid
    -0.59
     representations
    -0.59
     Rac
    -0.58
    plates
    -0.58
     Kinder
    -0.58
    POSITIVE LOGITS
     rethink
    1.18
     consult
    1.15
     consider
    1.12
     reconsider
    1.09
     revisit
    1.08
     emulate
    1.05
     invest
    1.03
     ignore
    1.02
     postpone
    0.99
     try
    0.98
    Activations Density 0.191%

    No Known Activations