© 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. 2707
    Prev
    Next
    INDEX
    Explanations

    references to real-time situations or technologies

    oai_token-act-pair · gpt-3.5-turbo

    references to real-life situations or experiences

    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
    xual
    -0.90
     Include
    -0.64
    Recommend
    -0.60
     Vaugh
    -0.60
    osi
    -0.60
     Pavilion
    -0.59
     overlooked
    -0.58
    rav
    -0.57
    indal
    -0.57
    theless
    -0.57
    POSITIVE LOGITS
    ignment
    1.41
     estate
    1.34
    isation
    1.24
    polit
    1.21
    estate
    1.19
    igning
    1.16
    igned
    1.16
    izations
    1.15
    DonaldTrump
    1.10
    ising
    1.09
    Activations Density 0.043%

    No Known Activations