INDEX

Explanations

adverbs indicating degree or intensity

oai_token-act-pair · gpt-3.5-turbo

phrases that express varying degrees of surprise or amazement

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

ature

-0.68

UME

-0.66

isher

-0.65

odder

-0.65

izu

-0.63

oris

-0.61

Ans

-0.60

agonists

-0.60

ograph

-0.59

uthor

-0.59

POSITIVE LOGITS

HCR

0.93

ls

0.87

soever

0.83

 much

0.81

ling

0.80

bill

0.77

beit

0.77

 MUCH

0.77

ells

0.76

much

0.75

Activations Density 0.083%

adverbs indicating degree or intensity

phrases that express varying degrees of surprise or amazement

No Comments

No Known Activations