© 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. 2-RES-JB
    11. 9510
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or political actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating accountability or consequences related to actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ety
    -0.55
    ¬¼
    -0.55
    herent
    -0.52
    iku
    -0.49
    rack
    -0.49
    inately
    -0.48
    sylv
    -0.47
    aza
    -0.47
    estones
    -0.47
     corrid
    -0.47
    POSITIVE LOGITS
     albeit
    0.88
     namely
    0.76
     Kinnikuman
    0.75
     although
    0.74
     including
    0.69
     etc
    0.68
     which
    0.65
     aka
    0.65
     however
    0.63
     according
    0.62
    Activations Density 1.295%

    No Known Activations