© 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. 10-RES-JB
    11. 14093
    Prev
    Next
    INDEX
    Explanations

    news stories or updates

    oai_token-act-pair · gpt-3.5-turbo

    the concept of news stories and reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    viation
    -0.65
    ;;;;;;;;;;;;
    -0.62
    ments
    -0.58
    ersen
    -0.57
    =-=-=-=-
    -0.56
    lessness
    -0.55
     Kessler
    -0.54
    given
    -0.54
    eering
    -0.54
    isoft
    -0.53
    POSITIVE LOGITS
    hots
    0.81
    IDER
    0.77
    matter
    0.67
    ider
    0.66
     sidel
    0.66
     tagged
    0.64
    mith
    0.63
    ospons
    0.61
    hig
    0.60
     trending
    0.60
    Activations Density 0.034%

    No Known Activations