INDEX

Explanations

comparisons indicating superiority or emphasis

oai_token-act-pair · gpt-3.5-turbo

instances of the word "more" and its comparative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

xtap

-0.80

atan

-0.75

heid

-0.72

etimes

-0.72

rosis

-0.68

pex

-0.68

æ©

-0.67

utions

-0.67

ovies

-0.66

OCK

-0.66

POSITIVE LOGITS

 than

1.37

 efficient

1.07

 likely

1.02

 complicated

1.02

 importantly

0.96

 inclined

0.96

 accurate

0.93

 expensive

0.91

 suited

0.90

 important

0.90

Activations Density 0.126%

comparisons indicating superiority or emphasis

instances of the word "more" and its comparative context

No Comments

No Known Activations