© 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. 2685
    Prev
    Next
    INDEX
    Explanations

    negative statements about a situation or a claim

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize negation or contrast

    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
    luaj
    -0.75
    named
    -0.69
     Named
    -0.60
    ukong
    -0.59
    regate
    -0.59
     maiden
    -0.58
    ierce
    -0.58
     Repair
    -0.56
    miah
    -0.56
    isively
    -0.55
    POSITIVE LOGITS
     irrelevant
    0.87
     nowhere
    0.75
     nonetheless
    0.74
     untrue
    0.73
     hardly
    0.70
     unlikely
    0.69
     unavoidable
    0.69
     alright
    0.67
     nevertheless
    0.67
     outwe
    0.66
    Activations Density 0.151%

    No Known Activations