INDEX

Explanations

words related to specific geographical locations or organizations

oai_token-act-pair · gpt-3.5-turbo

possessive forms indicating belonging or association

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ording

-0.81

ucl

-0.80

linux

-0.76

iaries

-0.75

ĳå£«

-0.73

rons

-0.73

object

-0.73

èĢħ

-0.72

oyle

-0.72

folios

-0.71

POSITIVE LOGITS

 finest

0.98

 newest

0.95

own

0.94

 largest

0.89

 poorest

0.89

 biggest

0.88

 burgeoning

0.87

 famed

0.86

 tallest

0.84

 wealthiest

0.83

Activations Density 0.087%

words related to specific geographical locations or organizations

possessive forms indicating belonging or association

No Comments

No Known Activations