INDEX

Explanations

conjunctions, specifically the word "and."

oai_token-act-pair · gpt-3.5-turbo

the conjunction "And" indicating connections between ideas or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ãģĨ

-0.75

ses

-0.71

ciples

-0.68

odcast

-0.67

-0.65

FIELD

-0.64

ELD

-0.64

HOU

-0.63

houses

-0.63

ema

-0.63

POSITIVE LOGITS

romeda

1.31

 furthermore

1.18

 secondly

1.09

hra

1.00

rea

0.98

 yeah

0.95

 moreover

0.92

 THEN

0.92

 vice

0.91

 then

0.88

Activations Density 0.083%

conjunctions, specifically the word "and."

the conjunction "And" indicating connections between ideas or events

No Comments

No Known Activations