INDEX

Explanations

ordinal rankings or positions

oai_token-act-pair · gpt-3.5-turbo

rankings and numerical positions related to performance metrics or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ellar

-0.71

tails

-0.70

ĨĴ

-0.66

 resusc

-0.64

imore

-0.63

ibus

-0.61

aton

-0.60

 shed

-0.59

eez

-0.58

ipation

-0.57

POSITIVE LOGITS

Tier

0.86

verages

0.80

BuyableInstoreAndOnline

0.77

incial

0.74

 percentile

0.71

 Highest

0.71

 athlet

0.71

ustom

0.68

 "$:/

0.68

retty

0.66

Activations Density 0.211%

ordinal rankings or positions

rankings and numerical positions related to performance metrics or statistics

No Comments

No Known Activations