INDEX

Explanations

words related to lack of knowledge or awareness, specifically focusing on the word "ignorant."

oai_token-act-pair · gpt-3.5-turbo

terms related to ignorance and lack of awareness

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

hetti

-0.77

ccording

-0.73

bourg

-0.70

gran

-0.68

ickr

-0.68

lished

-0.66

igsaw

-0.65

deen

-0.65

Textures

-0.63

emetery

-0.62

POSITIVE LOGITS

ingly

1.00

ness

0.90

uania

0.87

ledge

0.75

lust

0.75

nesses

0.74

 Leilan

0.72

äºĶ

0.72

lect

0.71

poke

0.70

Activations Density 0.030%

words related to lack of knowledge or awareness, specifically focusing on the word "ignorant."

terms related to ignorance and lack of awareness

No Comments

No Known Activations