INDEX

Explanations

phrases indicating a strong emphasis or recommendation

oai_token-act-pair · gpt-3.5-turbo

repeated instances of the word "so."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

works

-0.66

 Camel

-0.62

 Landing

-0.61

ership

-0.61

TTL

-0.59

 Dive

-0.59

osterone

-0.57

atform

-0.56

nings

-0.56

layer

-0.56

POSITIVE LOGITS

bered

1.28

iled

1.14

oths

1.04

othe

1.04

 powerfully

0.96

 badly

0.96

 desperately

0.96

 closely

0.96

 blatantly

0.95

 vehemently

0.95

Activations Density 0.057%

phrases indicating a strong emphasis or recommendation

repeated instances of the word "so."

No Comments

No Known Activations