INDEX

Explanations

the word "marsh" with strong emphasis

oai_token-act-pair · gpt-3.5-turbo

variations of the word "marshmallow."

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

 deaf

-0.83

wcs

-0.77

 livest

-0.73

hedral

-0.70

 thumbs

-0.68

 tense

-0.67

versions

-0.67

 vest

-0.66

ggle

-0.66

 inert

-0.64

POSITIVE LOGITS

mallow

1.83

alling

1.19

alled

1.05

aling

1.01

adow

0.99

alls

0.94

als

0.93

lands

0.91

ateur

0.91

 Marshal

0.90

Activations Density 0.016%

the word "marsh" with strong emphasis

variations of the word "marshmallow."

No Comments

No Known Activations