INDEX

Explanations

phrases where something is being compared or likened to something else using the word "like"

oai_token-act-pair · gpt-3.5-turbo

comparative phrases that introduce examples or similarities

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

ombat

-0.89

icter

-0.82

icator

-0.78

enary

-0.77

itiz

-0.75

utor

-0.71

aley

-0.71

iatus

-0.70

icators

-0.70

resy

-0.69

POSITIVE LOGITS

lihood

1.24

lier

0.87

liest

0.80

 ours

0.78

minded

0.74

 preferring

0.66

 those

0.64

 yours

0.62

 evidenced

0.62

 hypertension

0.62

Activations Density 0.076%

phrases where something is being compared or likened to something else using the word "like"

comparative phrases that introduce examples or similarities

No Comments

No Known Activations