INDEX

Explanations

words ending in "ing"

oai_token-act-pair · gpt-3.5-turbo

words related to actions and activities, particularly those ending with 'ing'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ascript

-0.79

å£

-0.70

osate

-0.69

 Leilan

-0.65

 captcha

-0.64

igslist

-0.61

ngth

-0.60

ACP

-0.60

ãĥ¤

-0.60

phabet

-0.59

POSITIVE LOGITS

redients

1.20

tons

1.03

lass

1.03

roup

0.85

borough

0.84

uez

0.81

ering

0.81

mire

0.81

rad

0.79

hoff

0.78

Activations Density 0.044%

words ending in "ing"

words related to actions and activities, particularly those ending with 'ing'

No Comments

No Known Activations