INDEX

Explanations

phrases expressing various degrees of evaluation or judgment, particularly focusing on the phrase "at best"

oai_token-act-pair · gpt-3.5-turbo

phrases indicating varying degrees of quality or effectiveness

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

selves

-0.68

condition

-0.61

ISH

-0.61

forth

-0.61

illance

-0.60

lish

-0.60

FTWARE

-0.59

oku

-0.58

HAM

-0.58

endum

-0.57

POSITIVE LOGITS

 times

1.25

 best

1.02

 least

0.89

 heart

0.88

 worst

0.88

mosp

0.83

 first

0.82

olls

0.80

onal

0.79

 odds

0.74

Activations Density 0.086%

phrases expressing various degrees of evaluation or judgment, particularly focusing on the phrase "at best"

phrases indicating varying degrees of quality or effectiveness

No Comments

No Known Activations