INDEX

Explanations

occurrences of the word "read" in different contexts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "read" and variations related to reading data or instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ascal

-0.69

Ã±o

-0.67

 Goodman

-0.67

Ø§ÙĦ

-0.66

ackle

-0.66

Truth

-0.66

Zur

-0.62

Credit

-0.61

qqa

-0.58

oteric

-0.58

POSITIVE LOGITS

 aloud

1.14

just

1.06

ied

1.03

dress

1.00

ying

1.00

 comprehension

0.95

mitt

0.85

ahead

0.84

iness

0.82

write

0.82

Activations Density 0.031%

occurrences of the word "read" in different contexts

instances of the word "read" and variations related to reading data or instructions

No Comments

No Known Activations