INDEX

Explanations

specific characters or symbols in a text

oai_token-act-pair · gpt-3.5-turbo

occurrences of a specific character or symbol used in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

espie

-0.77

wagen

-0.75

 Wilmington

-0.72

 Hurricanes

-0.71

intendent

-0.70

EMENT

-0.67

 guiActiveUnfocused

-0.67

terday

-0.66

 Freddie

-0.65

 Coliseum

-0.63

POSITIVE LOGITS

ģ

1.23

Ĵ

1.17

½

1.12

»

1.06

¾

1.04

ļ

1.04

Ĥ

1.03

ı

1.03

Į

1.03

¼

1.01

Activations Density 0.005%

specific characters or symbols in a text

occurrences of a specific character or symbol used in various contexts

No Comments

No Known Activations