© 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. 4583
    Prev
    Next
    INDEX
    Explanations

    specific entities or items of interest within a legal or legislative context

    oai_token-act-pair · gpt-3.5-turbo

    references to significant historical or legal documents and their 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
    lder
    -0.67
    isitions
    -0.66
    ittens
    -0.65
    ulas
    -0.64
    idents
    -0.62
    amina
    -0.61
    ceptions
    -0.60
    enses
    -0.59
    doms
    -0.59
    acters
    -0.59
    POSITIVE LOGITS
     whereby
    1.28
     wherein
    1.05
     titled
    1.04
     involving
    0.94
     indicating
    0.93
     consisting
    0.91
     featuring
    0.90
     outlining
    0.90
     depicting
    0.81
     entitled
    0.79
    Activations Density 0.768%

    No Known Activations