INDEX

Explanations

verbs related to proving or demonstrating something

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "prove to."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

é¾įåĸļå£«

-0.66

 managed

-0.65

ioch

-0.64

 allotted

-0.63

.–

-0.62

FIELD

-0.60

blooded

-0.60

cell

-0.60

 wastes

-0.59

estyles

-0.58

POSITIVE LOGITS

wered

0.93

ggles

0.92

psy

0.89

us

0.87

asted

0.83

me

0.82

ilet

0.81

othy

0.74

asting

0.72

Dispatch

0.71

Activations Density 0.091%

verbs related to proving or demonstrating something

instances of the phrase "prove to."

No Comments

No Known Activations