© 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. 9069
    Prev
    Next
    INDEX
    Explanations

    references to drafts or documents

    oai_token-act-pair · gpt-3.5-turbo

    terms related to drafts and versions of documents or reports

    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
    inos
    -0.75
    outube
    -0.72
     fishes
    -0.69
     destro
    -0.68
     hungry
    -0.68
     thirsty
    -0.68
    udi
    -0.66
     rappers
    -0.65
    âĺĨ
    -0.64
     tourists
    -0.64
    POSITIVE LOGITS
     wording
    1.16
     regulations
    1.14
     guidelines
    1.10
     rules
    1.08
     legislation
    1.05
     draft
    1.05
     proposals
    1.04
     drafts
    1.04
     proposal
    1.00
     Regulations
    0.99
    Activations Density 0.233%

    No Known Activations