INDEX

Explanations

instances of the word "Jrzy" or variations of its spelling

oai_token-act-pair · gpt-3.5-turbo

words related to the concept of 'zy' or 'crazy' in various contexts

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

umbnails

-0.92

anooga

-0.82

ional

-0.79

ials

-0.74

angered

-0.74

eter

-0.71

iflower

-0.71

eters

-0.70

strong

-0.70

aul

-0.69

POSITIVE LOGITS

cki

0.94

zy

0.81

mbol

0.80

gie

0.79

usha

0.78

ZZ

0.75

zzy

0.74

zx

0.71

ÅĤ

0.70

ze

0.70

Activations Density 0.018%

instances of the word "Jrzy" or variations of its spelling

words related to the concept of 'zy' or 'crazy' in various contexts

No Comments

No Known Activations