INDEX

Explanations

comparisons between different concepts or entities

oai_token-act-pair · gpt-3.5-turbo

phrases related to societal structures and distinctions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Balt

-0.64

abouts

-0.63

cedented

-0.62

Moscow

-0.60

accompanied

-0.59

abled

-0.59

âĹ¼

-0.59

 Kazakh

-0.59

UPDATE

-0.59

"}

-0.58

POSITIVE LOGITS

 strive

0.92

 nurture

0.90

 obedience

0.78

 striving

0.77

 selfish

0.77

 cultivate

0.76

 mentors

0.73

 strives

0.73

 nurt

0.73

 coward

0.73

Activations Density 0.955%

comparisons between different concepts or entities

phrases related to societal structures and distinctions

No Comments

No Known Activations