INDEX

Explanations

proper nouns containing the sequence "agon"

oai_token-act-pair · gpt-3.5-turbo

words related to "agon" or competitive scenarios, particularly in sports and contests

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

-0.71

ples

-0.69

bered

-0.65

 Lori

-0.64

ensional

-0.61

natureconservancy

-0.59

uctor

-0.57

 borrower

-0.57

cedented

-0.56

 stressful

-0.55

POSITIVE LOGITS

naire

1.35

naires

0.97

xon

0.93

ocity

0.86

nel

0.84

otine

0.82

ous

0.81

arium

0.81

auts

0.80

ansas

0.79

Activations Density 0.014%

proper nouns containing the sequence "agon"

words related to "agon" or competitive scenarios, particularly in sports and contests

No Comments

No Known Activations