INDEX

Explanations

phrases related to bringing an "end" to various situations or conditions

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate the conclusion or cessation of policies or actions

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

DragonMagazine

-0.71

kaya

-0.65

rious

-0.64

 Maker

-0.63

dinand

-0.62

ickr

-0.61

itsch

-0.61

thouse

-0.61

rium

-0.60

hawk

-0.59

POSITIVE LOGITS

angering

1.26

owment

1.15

angered

0.87

angers

0.86

tackle

0.84

ocrin

0.82

orses

0.80

urable

0.80

ocrine

0.78

ENDED

0.76

Activations Density 0.043%

phrases related to bringing an "end" to various situations or conditions

phrases that indicate the conclusion or cessation of policies or actions

No Comments

No Known Activations