INDEX

Explanations

phrases related to awards, fellowships, and prestigious recognition

oai_token-act-pair · gpt-3.5-turbo

references to notable individuals and their associations with fellowships and filmmaking

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

store

-0.81

ctica

-0.70

ãĥĺ

-0.70

ãĤ¢ãĥ«

-0.69

Occup

-0.67

Store

-0.65

que

-0.65

ãĥķãĤ©

-0.63

pite

-0.62

ãĥ

-0.62

POSITIVE LOGITS

 Fell

1.15

 fellows

1.05

 Fellow

1.05

ees

0.90

hips

0.83

furt

0.78

inguished

0.78

 Fellowship

0.76

lasses

0.75

doctoral

0.74

Activations Density 0.013%

phrases related to awards, fellowships, and prestigious recognition

references to notable individuals and their associations with fellowships and filmmaking

No Comments

No Known Activations