INDEX

Explanations

phrases indicating different possibilities or alternatives

oai_token-act-pair · gpt-3.5-turbo

phrases that express alternatives or variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Wyn

-0.64

 Bere

-0.64

Alert

-0.62

 amateur

-0.60

 Reno

-0.59

ateur

-0.59

 skeptical

-0.57

 Werewolf

-0.56

Ket

-0.56

Lyn

-0.56

POSITIVE LOGITS

 circumstance

0.88

orld

0.86

 manner

0.83

 guise

0.78

ategory

0.76

 timeframe

0.76

foreseen

0.75

urrencies

0.74

isine

0.74

hra

0.74

Activations Density 0.148%

phrases indicating different possibilities or alternatives

phrases that express alternatives or variations

No Comments

No Known Activations