INDEX

Explanations

phrases related to priorities and importance

oai_token-act-pair · gpt-3.5-turbo

statements indicating levels of importance or priority

oai_token-act-pair · gpt-4o-mini Triggered by @bot

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

redited

-0.78

tiny

-0.75

sk

-0.74

redd

-0.73

Afee

-0.71

adem

-0.71

cap

-0.71

tub

-0.71

inally

-0.70

attering

-0.70

POSITIVE LOGITS

 priority

0.98

 priorities

0.95

 priorit

0.93

 prioritize

0.88

priority

0.87

 consideration

0.84

 duty

0.83

 Priority

0.79

 allocation

0.76

 allocations

0.68

Activations Density 0.028%

phrases related to priorities and importance

statements indicating levels of importance or priority

No Comments

No Known Activations