INDEX

Explanations

words related to temporal sequences or events

oai_token-act-pair · gpt-3.5-turbo

the word "when" indicating temporal references or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

agin

-0.69

kaya

-0.66

harm

-0.66

åĤ

-0.64

edly

-0.61

alian

-0.60

aking

-0.60

SPONSORED

-0.60

atic

-0.59

PHOTOS

-0.59

POSITIVE LOGITS

soever

1.38

 asked

0.89

 confronted

0.87

 pressed

0.80

irlf

0.79

 faced

0.76

 contacted

0.72

quickShipAvailable

0.72

phies

0.70

IPS

0.69

Activations Density 0.087%

words related to temporal sequences or events

the word "when" indicating temporal references or events

No Comments

No Known Activations