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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 6-RES-JB
    6. 7867
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or actions that occurred eventually

    oai_token-act-pair · gpt-3.5-turbo

    actions and outcomes related to events or processes that culminate in significant results or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Previous
    -0.72
     guiName
    -0.71
    cius
    -0.71
     Needs
    -0.70
     rog
    -0.70
     Normally
    -0.69
     tomorrow
    -0.66
     Variant
    -0.66
     TOD
    -0.65
    heit
    -0.64
    POSITIVE LOGITS
    sequently
    0.86
     unsuccessful
    0.83
     subsequent
    0.82
     memorable
    0.81
     succeeded
    0.79
     successfully
    0.78
     subsequently
    0.78
     thereafter
    0.78
     eventually
    0.76
     promptly
    0.75
    Activations Density 1.169%

    No Known Activations