© 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. 4-RES-JB
    11. 15342
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific aspects or considerations

    oai_token-act-pair · gpt-3.5-turbo

    phrases discussing various topics or issues with a focus on the term "regard" or its variations

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

    No Comments

    Negative Logits
     Masquerade
    -0.71
     Staten
    -0.66
    egg
    -0.65
     Brist
    -0.64
     frog
    -0.64
     pearl
    -0.63
     tatt
    -0.61
     submar
    -0.61
    mith
    -0.61
     ferry
    -0.61
    POSITIVE LOGITS
    rity
    0.89
    ability
    0.82
    ibly
    0.82
    enance
    0.80
    ibility
    0.80
    chery
    0.80
    ments
    0.79
    rients
    0.79
    ership
    0.79
    ibilities
    0.77
    Activations Density 0.022%

    No Known Activations