INDEX

Explanations

phrases indicating opposition or conflict

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "up in" within various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 withd

-0.66

âĦ¢:

-0.63

mes

-0.63

Äĩ

-0.63

velt

-0.63

chini

-0.62

Problem

-0.62

theless

-0.62

sson

-0.62

anty

-0.61

POSITIVE LOGITS

 flames

1.15

 smoke

0.85

 heaven

0.81

 front

0.81

 Flames

0.79

 arms

0.75

 leaps

0.75

animate

0.73

 handcuffs

0.70

 flame

0.69

Activations Density 0.079%

phrases indicating opposition or conflict

instances of the phrase "up in" within various contexts

No Comments

No Known Activations