INDEX

Explanations

commands or actions related to reading or writing data in a computer program

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "read."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

xon

-0.71

Ø§ÙĦ

-0.69

Ã±o

-0.67

 Goodman

-0.66

ackle

-0.65

ascal

-0.64

qqa

-0.63

Truth

-0.63

Zur

-0.62

addafi

-0.60

POSITIVE LOGITS

 aloud

1.13

just

1.13

ying

1.01

dress

0.98

ied

0.98

 comprehension

0.90

ifi

0.85

mill

0.83

minist

0.82

Write

0.82

Activations Density 0.037%

commands or actions related to reading or writing data in a computer program

occurrences of the word "read."

No Comments

No Known Activations