INDEX

Explanations

various forms of the word "chair."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Territories

-0.68

Adds

-0.67

actionDate

-0.67

DN

-0.64

 Rounds

-0.64

ï¸ı

-0.63

 Sabb

-0.62

 Partnership

-0.61

 tolerance

-0.61

ONEY

-0.60

POSITIVE LOGITS

lift

1.38

chair

1.07

holder

1.05

 chair

0.98

manship

0.97

tops

0.97

 cush

0.92

chairs

0.91

lain

0.91

 chairs

0.90

Activations Density 0.010%

various forms of the word "chair."

No Comments

No Known Activations