© 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. 20717
    Prev
    Next
    INDEX
    Explanations

    advertisements prompting the reader to continue reading a main story

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the continuation of reading or engagement

    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
    ranch
    -0.91
    otom
    -0.78
    istered
    -0.77
    rams
    -0.74
    estic
    -0.73
    bid
    -0.66
    aster
    -0.65
    ura
    -0.65
    naire
    -0.64
    ramid
    -0.63
    POSITIVE LOGITS
     Continued
    1.02
     Continue
    0.97
    CLASSIFIED
    0.95
    ...]
    0.91
     Advertisement
    0.82
     Loading
    0.78
     Transcript
    0.77
     Occupations
    0.75
     Thumbnails
    0.71
     convol
    0.71
    Activations Density 0.013%

    No Known Activations