© 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. 2-RES-JB
    11. 9317
    Prev
    Next
    INDEX
    Explanations

    references to the majority or most common occurrences in a given context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "most."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pload
    -0.74
    pless
    -0.72
    rompt
    -0.70
     CARD
    -0.66
    pton
    -0.65
     guiActiveUnfocused
    -0.62
    thur
    -0.62
    arium
    -0.61
    pt
    -0.60
     LOT
    -0.60
    POSITIVE LOGITS
     importantly
    1.06
     Helpful
    0.94
     Wanted
    0.89
    entimes
    0.86
     Likely
    0.85
     Important
    0.84
     important
    0.83
    likely
    0.81
     notable
    0.79
    body
    0.78
    Activations Density 0.039%

    No Known Activations