INDEX

Explanations

phrases indicating positive emotions

oai_token-act-pair · gpt-3.5-turbo

expressions of feeling good or positive sentiments

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

 distinguished

-0.65

 favoured

-0.62

 pioneered

-0.61

location

-0.60

erity

-0.59

 disadvantage

-0.59

haps

-0.58

Lif

-0.58

 coveted

-0.58

hip

-0.57

POSITIVE LOGITS

stories

0.88

ãĤ´

0.85

ALLY

0.73

 lapt

0.70

:)

0.66

andi

0.66

waves

0.65

puff

0.64

enough

0.62

locks

0.61

Activations Density 0.062%

phrases indicating positive emotions

expressions of feeling good or positive sentiments

No Comments

No Known Activations