INDEX

Explanations

the word "do" in various contexts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "do" in various contexts

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

dayName

-0.77

lights

-0.76

 Canal

-0.66

mares

-0.66

liner

-0.65

ricted

-0.65

hog

-0.63

pac

-0.63

uru

-0.63

)=(

-0.62

POSITIVE LOGITS

omsday

1.02

omething

0.97

ozy

0.89

ppel

0.89

pez

0.88

lez

0.85

vet

0.77

xy

0.77

oley

0.77

oway

0.76

Activations Density 0.093%

the word "do" in various contexts

instances of the word "do" in various contexts

No Comments

No Known Activations