INDEX

Explanations

keywords related to reading and writing data in a technical context

oai_token-act-pair · gpt-3.5-turbo

instances of reading and writing actions or functions in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

xon

-0.71

opard

-0.63

 Gamble

-0.59

Ã±o

-0.58

Las

-0.58

 halftime

-0.58

Ø§ÙĦ

-0.57

Zur

-0.57

 rolling

-0.56

ality

-0.55

POSITIVE LOGITS

 aloud

1.40

just

1.28

 comprehension

1.13

ying

1.11

write

1.08

dress

1.06

mission

1.04

ahead

1.03

mitted

1.01

ied

1.00

Activations Density 0.053%

keywords related to reading and writing data in a technical context

instances of reading and writing actions or functions in a technical context

No Comments

No Known Activations