INDEX

Explanations

articles followed by words starting with the letter 'a'

oai_token-act-pair · gpt-3.5-turbo

assertive or declarative statements indicating significance

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

Edit

-0.85

items

-0.78

chuk

-0.75

Gray

-0.73

bots

-0.71

otte

-0.70

olicy

-0.70

DOM

-0.69

Show

-0.68

units

-0.67

POSITIVE LOGITS

 fascinating

1.06

 worthwhile

0.96

 simple

0.95

 huge

0.94

 coincidence

0.94

 constant

0.92

 reminder

0.92

 nice

0.91

 consolation

0.91

lot

0.90

Activations Density 0.170%

articles followed by words starting with the letter 'a'

assertive or declarative statements indicating significance

No Comments

No Known Activations