INDEX

Explanations

words or phrases related to changes, mysteries, or disappearances

oai_token-act-pair · gpt-3.5-turbo

statements regarding facts, descriptions, and attributes of specific subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 absentee

-0.71

ember

-0.70

afi

-0.67

 dividends

-0.65

 pensions

-0.65

 Universities

-0.64

 salaries

-0.64

iosyncr

-0.64

querque

-0.63

blogs

-0.63

POSITIVE LOGITS

eus

0.79

washer

0.78

Rot

0.75

Recipe

0.68

ãĥĺ

0.66

bis

0.66

 Thrust

0.65

uron

0.62

Hit

0.62

 itself

0.62

Activations Density 0.847%

words or phrases related to changes, mysteries, or disappearances

statements regarding facts, descriptions, and attributes of specific subjects

No Comments

No Known Activations