© 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. 3311
    Prev
    Next
    INDEX
    Explanations

    phrases that involve breaking down information or processes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "breakdown" and related terms indicating analysis or dissection of topics

    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
    qua
    -0.76
    ñ
    -0.76
    geon
    -0.75
    nee
    -0.74
    otto
    -0.73
    cot
    -0.70
    Shar
    -0.70
    esthetic
    -0.69
    ña
    -0.69
    eno
    -0.69
    POSITIVE LOGITS
     breakdown
    1.35
     conversions
    0.91
    DOWN
    0.81
     arrang
    0.79
    sie
    0.78
     tables
    0.77
     stru
    0.76
     arrangements
    0.76
     diagrams
    0.76
     STATS
    0.71
    Activations Density 0.006%

    No Known Activations