INDEX

Explanations

descriptions of places, events, or situations where different elements are compared on a scale

oai_token-act-pair · gpt-3.5-turbo

words and phrases related to events, specifically attendance and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 doesnt

-0.57

"))

-0.54

 NEVER

-0.52

 didnt

-0.52

©¶æ

-0.50

MIS

-0.47

)))

-0.47

 ALWAYS

-0.47

tyr

-0.47

 TOTAL

-0.45

POSITIVE LOGITS

1.17

.;

1.05

but

0.95

,[

0.94

—

0.93

0.90

.)

0.89

.[

0.89

—"

0.88

Activations Density 1.418%

descriptions of places, events, or situations where different elements are compared on a scale

words and phrases related to events, specifically attendance and locations

No Comments

No Known Activations