Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 23399
    Prev
    Next
    INDEX
    Explanations

    phrases related to perspectives or attitudes

    oai_token-act-pair · gpt-3.5-turbo

    words related to forecasts or expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lawfully
    -0.77
     unlawfully
    -0.70
    ibly
    -0.68
    Invalid
    -0.66
    poke
    -0.64
     Fast
    -0.63
    Fast
    -0.62
    DOM
    -0.59
     illegally
    -0.58
    ãĥĺ
    -0.58
    POSITIVE LOGITS
     outlook
    3.79
     Outlook
    1.70
     worldview
    1.37
     attitude
    1.32
     optimism
    1.32
     forecast
    1.25
     mindset
    1.23
     perspectives
    1.20
     horizon
    1.18
     perspective
    1.18
    Activations Density 0.005%

    No Known Activations