INDEX

Explanations

the word "is" in sentences

oai_token-act-pair · gpt-3.5-turbo

affirmative statements or declarations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ethy

-0.82

OTO

-0.76

morph

-0.74

 Defin

-0.74

 actionGroup

-0.73

nesia

-0.73

orph

-0.72

oglu

-0.71

dinand

-0.70

ijn

-0.69

POSITIVE LOGITS

Weather

0.70

Deal

0.66

 kindly

0.62

Wen

0.61

!]

0.61

 unbiased

0.59

 lowly

0.59

 aven

0.58

 Grimm

0.58

 ratio

0.56

Activations Density 0.000%

the word "is" in sentences

affirmative statements or declarations

No Comments

No Known Activations