© 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. 8303
    Prev
    Next
    INDEX
    Explanations

    phrases related to supervision and oversight

    oai_token-act-pair · gpt-3.5-turbo
    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
    orians
    -0.78
    orian
    -0.75
    hner
    -0.72
    endor
    -0.71
    tery
    -0.69
    blank
    -0.69
    ml
    -0.68
    growth
    -0.68
    UES
    -0.68
    hon
    -0.67
    POSITIVE LOGITS
     supervision
    1.33
     supervised
    1.10
     superv
    0.99
     probation
    0.92
     oversee
    0.89
     confir
    0.86
     conduc
    0.85
     Instruct
    0.76
     overseen
    0.74
     overseeing
    0.71
    Activations Density 0.011%

    No Known Activations