INDEX

Explanations

personal pronouns, verbs of speech, and expressions of uncertainty and opinion

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

 Additional

-0.74

SpaceEngineers

-0.72

 guiActiveUnfocused

-0.70

arthed

-0.69

 undisclosed

-0.69

"}],"

-0.68

"},"

-0.67

rocal

-0.67

cedented

-0.67

"))

-0.66

POSITIVE LOGITS

 certainly

0.88

 honestly

0.81

 pity

0.81

 kidding

0.79

 wonder

0.79

oret

0.78

cknow

0.76

 sure

0.75

Sure

0.74

Think

0.74

Activations Density 2.171%

personal pronouns, verbs of speech, and expressions of uncertainty and opinion

No Comments

No Known Activations