INDEX

Explanations

iterations of the French word "je" which means "I" in English

oai_token-act-pair · gpt-3.5-turbo

the occurrence of the word "je" and related variants

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

raviolet

-0.81

ancial

-0.80

ãĥ´ãĤ¡

-0.79

 Dull

-0.70

å§«

-0.65

Interstitial

-0.64

ctrl

-0.62

holders

-0.62

alysis

-0.62

ntil

-0.62

POSITIVE LOGITS

hovah

1.48

je

1.14

ijn

0.87

eps

0.87

opard

0.86

ep

0.80

ij

0.76

ques

0.75

neys

0.75

quet

0.74

Activations Density 0.004%

iterations of the French word "je" which means "I" in English

the occurrence of the word "je" and related variants

No Comments

No Known Activations