© 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. 1-RES-JB
    11. 3278
    Prev
    Next
    INDEX
    Explanations

    phrases related to breaking or breaking through a barrier

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "break."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.82
    ulp
    -0.75
     redistributed
    -0.71
     stocking
    -0.71
    «ĺ
    -0.70
     pric
    -0.66
     compuls
    -0.65
     eleph
    -0.63
     deduction
    -0.62
     plurality
    -0.62
    POSITIVE LOGITS
    break
    1.26
    fast
    1.19
    breaking
    1.00
    breakers
    0.95
    Berry
    0.92
    through
    0.91
    tenance
    0.87
    beat
    0.84
    water
    0.83
    breaks
    0.83
    Activations Density 0.009%

    No Known Activations