© 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. 6-RES-JB
    11. 21827
    Prev
    Next
    INDEX
    Explanations

    statements related to human behavior or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating human behavior and social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -1.02
    oshenko
    -0.66
     CRC
    -0.65
    ouse
    -0.64
    Applic
    -0.64
     HF
    -0.61
    iquid
    -0.60
    tek
    -0.60
    Owner
    -0.60
    MAP
    -0.57
    POSITIVE LOGITS
     ourselves
    1.26
     democracies
    0.81
     selves
    0.77
     electing
    0.75
     asses
    0.75
     reckoning
    0.75
     mortals
    0.73
     collectively
    0.73
     ours
    0.72
    enment
    0.71
    Activations Density 0.438%

    No Known Activations