INDEX

Explanations

common words used in problem-solving contexts

oai_token-act-pair · gpt-3.5-turbo

phrases containing the word "that."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

Returns

-0.67

OV

-0.64

LET

-0.62

ATH

-0.61

INST

-0.61

NES

-0.60

REDACTED

-0.59

ISON

-0.59

thumbnails

-0.59

ther

-0.58

POSITIVE LOGITS

are

1.27

 were

1.26

 aren

1.25

 weren

1.25

 comprise

1.17

 arise

1.14

 circulate

1.13

 characterize

1.12

 constitute

1.12

 relate

1.12

Activations Density 0.212%

common words used in problem-solving contexts

phrases containing the word "that."

No Comments

No Known Activations