INDEX

Explanations

first-person singular pronouns followed by verbs indicating leading or guiding actions

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ese

-0.75

ary

-0.71

RP

-0.62

Enlarge

-0.62

 supplied

-0.61

YY

-0.60

BR

-0.59

 sorted

-0.59

ially

-0.59

yz

-0.58

POSITIVE LOGITS

 believe

1.03

 realize

0.86

 conclude

0.86

 conclusions

0.84

 realise

0.80

 pursue

0.79

 discover

0.77

 embrace

0.76

 contemplate

0.75

 extremes

0.73

Activations Density 0.161%

first-person singular pronouns followed by verbs indicating leading or guiding actions

No Comments

No Known Activations