© 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. 364
    Prev
    Next
    INDEX
    Explanations

    terms related to acts of giving up or letting go something valuable for a cause

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sacrifice" and 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
    realDonaldTrump
    -0.69
    Correct
    -0.68
     Cheong
    -0.67
    updated
    -0.67
    col
    -0.66
    Nap
    -0.66
     Hust
    -0.64
    WHO
    -0.64
    uzz
    -0.63
     Kamp
    -0.63
    POSITIVE LOGITS
     sacrifice
    1.10
     sacrificed
    1.10
    rifice
    1.08
    ificial
    0.98
     sacrific
    0.98
     sacrifices
    0.96
     sacrificing
    0.94
     altar
    0.82
     Sacrifice
    0.78
    rament
    0.78
    Activations Density 0.016%

    No Known Activations