INDEX

Explanations

personal pronouns followed by past tense verbs

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aea

-0.66

inery

-0.66

ious

-0.64

ful

-0.63

scription

-0.62

liness

-0.62

imon

-0.61

mental

-0.61

sequent

-0.60

development

-0.60

POSITIVE LOGITS

 goes

0.75

eps

0.74

go

0.67

 went

0.64

 stands

0.62

 sits

0.61

eka

0.60

olini

0.60

 belonged

0.59

ÅĤ

0.59

Activations Density 0.060%

personal pronouns followed by past tense verbs

No Comments

No Known Activations