INDEX

Explanations

proper names, likely the name "Isaac"

oai_token-act-pair · gpt-3.5-turbo

instances of the name "Isaac" and associated prominence

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

marked

-0.92

lain

-0.88

ĸļ

-0.81

olulu

-0.79

emonium

-0.78

efully

-0.77

eful

-0.77

ebook

-0.76

liness

-0.74

naire

-0.73

POSITIVE LOGITS

 Isaac

0.90

 Newton

0.88

antine

0.78

imov

0.75

Lev

0.74

 Hayes

0.74

 Dixon

0.73

 Hemp

0.70

hem

0.69

 Clarke

0.69

Activations Density 0.017%

proper names, likely the name "Isaac"

instances of the name "Isaac" and associated prominence

No Comments

No Known Activations