INDEX

Explanations

adjectives or nouns indicating an unavoidable or certain outcome

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

tein

-0.87

entin

-0.82

raph

-0.82

chel

-0.81

uay

-0.80

rongh

-0.80

emark

-0.80

abit

-0.79

burgh

-0.79

abase

-0.76

POSITIVE LOGITS

 doom

0.89

 consequence

0.86

 culmin

0.82

 inev

0.78

 arises

0.77

 downfall

0.76

NULL

0.74

 arise

0.71

 Cruel

0.71

 conclusion

0.71

Activations Density 0.059%

adjectives or nouns indicating an unavoidable or certain outcome

No Comments

No Known Activations

adjectives or nouns indicating an unavoidable or certain outcome

No Comments

No Known Activations