INDEX

Explanations

terms related to the concept of "impression", particularly focusing on expressing opinions or beliefs about something or someone

oai_token-act-pair · gpt-3.5-turbo

phrases related to the concept of 'impression'

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

atts

-0.76

annis

-0.72

vez

-0.70

cross

-0.68

foreseen

-0.66

fighting

-0.65

undreds

-0.62

regulated

-0.60

cgi

-0.60

church

-0.60

POSITIVE LOGITS

 impression

1.04

 impressions

0.99

eful

0.89

eless

0.87

uren

0.84

izable

0.80

istic

0.79

able

0.77

ably

0.75

terness

0.72

Activations Density 0.041%

terms related to the concept of "impression", particularly focusing on expressing opinions or beliefs about something or someone

phrases related to the concept of 'impression'

No Comments

No Known Activations