INDEX

Explanations

phrases related to academic degrees and research

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

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

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TMZ

-0.74

bite

-0.72

grounds

-0.70

ground

-0.65

ãĥ¼ãĥ³

-0.65

theless

-0.65

 indec

-0.63

limit

-0.63

Peb

-0.62

ideshow

-0.62

POSITIVE LOGITS

 dissertation

1.30

 thesis

1.20

uates

1.01

 doctoral

0.95

essor

0.93

 graduate

0.90

ertation

0.89

 resear

0.85

hai

0.85

 student

0.82

Activations Density 0.017%

phrases related to academic degrees and research

No Comments

No Known Activations