© 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. 6152
    Prev
    Next
    INDEX
    Explanations

    family relationships and details about family members

    oai_token-act-pair · gpt-3.5-turbo

    mentions of family relationships and connections

    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
    oster
    -0.74
    ocally
    -0.62
    ost
    -0.61
    izophren
    -0.61
    ilipp
    -0.61
    committee
    -0.60
    etting
    -0.60
    avorable
    -0.60
    Critics
    -0.59
    ocations
    -0.59
    POSITIVE LOGITS
     whom
    0.99
     Jr
    0.94
     eldest
    0.92
     who
    0.90
    daughter
    0.85
    Jr
    0.84
     Sr
    0.84
     daughter
    0.82
     married
    0.82
     aka
    0.80
    Activations Density 0.196%

    No Known Activations