INDEX

Explanations

phrases related to certainty and action

oai_token-act-pair · gpt-3.5-turbo

repetitive phrases emphasizing what one can expect or receive

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 strikingly

-0.60

xtap

-0.59

 Cosponsors

-0.57

orically

-0.56

 Gallup

-0.56

zsche

-0.54

ourse

-0.52

 Historically

-0.52

earcher

-0.52

 anecd

-0.51

POSITIVE LOGITS

âĢ¦."

0.88

 gonna

0.86

)."

0.86

âĢ¦"

0.84

..."

0.84

))))

0.82

 fuckin

0.80

-"

0.79

.'"

0.79

 âĢ¦"

0.78

Activations Density 1.082%

phrases related to certainty and action

repetitive phrases emphasizing what one can expect or receive

No Comments

No Known Activations