INDEX

Explanations

words and phrases related to symbolism and being indicative or suggestive

oai_token-act-pair · gpt-3.5-turbo

terms related to symbolism and suggestiveness in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

frey

-0.84

hard

-0.70

bill

-0.67

bury

-0.66

flies

-0.66

foreseen

-0.66

hung

-0.66

AF

-0.65

bag

-0.65

hardt

-0.65

POSITIVE LOGITS

hetically

0.84

hetical

0.80

ively

0.76

 antioxid

0.74

wcs

0.73

 surpr

0.72

CPC

0.72

 undermin

0.66

 advoc

0.66

matically

0.66

Activations Density 0.046%

words and phrases related to symbolism and being indicative or suggestive

terms related to symbolism and suggestiveness in context

No Comments

No Known Activations