INDEX

Explanations

phrases related to the cessation of habitual actions or behaviors

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ortment

-0.66

maximum

-0.66

odan

-0.61

romy

-0.57

 bounty

-0.57

 Horus

-0.56

gged

-0.55

pta

-0.55

xtap

-0.54

eer

-0.54

POSITIVE LOGITS

 than

0.92

nces

0.80

ONSORED

0.79

;)

0.78

adays

0.77

!!!!!

0.76

!!!

0.75

:(

0.74

:-)

0.73

iatus

0.73

Activations Density 0.021%

phrases related to the cessation of habitual actions or behaviors

No Comments

No Known Activations