INDEX

Explanations

superlative forms indicating the highest degree or extent of something

oai_token-act-pair · gpt-3.5-turbo

the word "most," emphasizing its usage in various contexts throughout the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

asar

-0.68

 WRITE

-0.61

 Sands

-0.60

urches

-0.59

 CARD

-0.59

instead

-0.58

 Tanz

-0.58

 Palace

-0.57

CHR

-0.57

 trilogy

-0.56

POSITIVE LOGITS

 importantly

1.27

 likely

1.15

likely

1.05

 notably

1.04

 certainly

1.04

 assured

1.03

 definitely

1.01

afa

0.95

 prominently

0.92

 Likely

0.85

Activations Density 0.061%

superlative forms indicating the highest degree or extent of something

the word "most," emphasizing its usage in various contexts throughout the document

No Comments

No Known Activations