INDEX

Explanations

phrases related to negative events or situations

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a decline or downfall

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.83

thood

-0.81

license

-0.79

ãģķ

-0.76

Cola

-0.73

untarily

-0.72

©¶æ¥µ

-0.71

olphin

-0.71

catentry

-0.71

poon

-0.71

POSITIVE LOGITS

 unfold

0.83

 downhill

0.78

 suspense

0.75

 pandemonium

0.75

:#

0.73

 unfolding

0.71

 intrigue

0.69

 Mayhem

0.69

 Hayes

0.68

 mayhem

0.68

Activations Density 1.076%

phrases related to negative events or situations

phrases indicating a decline or downfall

No Comments

No Known Activations