INDEX

Explanations

extremes in numerical values such as 'lowest' or 'highest'

oai_token-act-pair · gpt-3.5-turbo

phrases indicating extreme quantitative values, specifically highs and lows in various metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

èĪ

-0.74

enegger

-0.70

 Nightmares

-0.67

pron

-0.66

umbn

-0.65

oras

-0.65

tiny

-0.64

cult

-0.64

rio

-0.63

Cho

-0.62

POSITIVE LOGITS

 ever

1.21

ever

1.18

 EVER

1.13

 since

0.95

 recorded

0.93

 imaginable

0.85

Ever

0.83

 mark

0.82

 Ever

0.81

 tally

0.80

Activations Density 0.126%

extremes in numerical values such as 'lowest' or 'highest'

phrases indicating extreme quantitative values, specifically highs and lows in various metrics

No Comments

No Known Activations