INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter "A" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

orate

-0.75

idge

-0.67

ãĥ³

-0.60

EngineDebug

-0.60

unction

-0.58

enegger

-0.58

ptions

-0.57

ItemImage

-0.57

ictions

-0.57

fry

-0.54

POSITIVE LOGITS

2.60

An

1.63

1.51

AN

1.06

As

1.05

At

1.03

AA

1.02

0.99

 Another

0.98

One

0.98

Activations Density 0.046%

proper nouns

occurrences of the letter "A" in various contexts

No Comments

No Known Activations