© 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. 12818
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the start of a new discussion or point, sometimes followed by a response

    oai_token-act-pair · gpt-3.5-turbo

    the word "Well" in various contexts

    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
    illary
    -0.86
    İĭ
    -0.69
    âĹ¼
    -0.67
    adena
    -0.63
     flair
    -0.62
    dash
    -0.62
    hyde
    -0.61
     arom
    -0.60
    Gy
    -0.60
     dash
    -0.59
    POSITIVE LOGITS
    esley
    1.00
    come
    0.87
    espie
    0.86
    ington
    0.83
    ness
    0.81
    tenance
    0.80
     Enough
    0.78
    ega
    0.77
    nesses
    0.75
    ERE
    0.74
    Activations Density 0.024%

    No Known Activations