© 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. 8-RES-JB
    11. 6253
    Prev
    Next
    INDEX
    Explanations

    phrases related to information being revealed or disclosed

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "coming out of" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mercial
    -0.74
    htaking
    -0.71
     Ranking
    -0.68
     challeng
    -0.67
    xual
    -0.67
    iveness
    -0.64
    escription
    -0.63
    uploads
    -0.60
    iques
    -0.60
    ignt
    -0.60
    POSITIVE LOGITS
     nowhere
    1.17
     hiding
    0.75
    Solid
    0.69
     pockets
    0.68
    zag
    0.67
     thin
    0.67
    isp
    0.64
    ifice
    0.64
     hiber
    0.63
    RH
    0.62
    Activations Density 0.104%

    No Known Activations