INDEX

Explanations

phrases related to events or situations described as extraordinary

oai_token-act-pair · gpt-3.5-turbo

the term "extraordinary" in various contexts throughout the document

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

©¶æ

-0.86

hr

-0.85

hn

-0.82

worn

-0.77

rio

-0.74

hm

-0.71

iewicz

-0.70

Ķ

-0.70

gage

-0.70

hl

-0.70

POSITIVE LOGITS

 rendition

1.18

ordinary

1.02

 heroism

0.94

 coincidence

0.93

 feats

0.89

 lengths

0.86

 extraordinary

0.80

 leaps

0.80

 amounts

0.80

 Measures

0.79

Activations Density 0.022%

phrases related to events or situations described as extraordinary

the term "extraordinary" in various contexts throughout the document

No Comments

No Known Activations