INDEX

Explanations

phrases related to technical instructions or descriptions

oai_token-act-pair · gpt-3.5-turbo

specific characters or symbols, particularly variations of the letter 'l'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Negro

-0.84

 Reverend

-0.83

 scandals

-0.78

 imperialist

-0.77

 Jama

-0.76

 flourishing

-0.75

 disgrace

-0.75

 disgr

-0.75

 outraged

-0.74

 Jihad

-0.74

POSITIVE LOGITS

ï¸ı

1.42

ï¸

1.09

âĹ

1.05

Â§

1.00

â

0.97

Â£

0.97

âĸ

0.95

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

0.95

Unique

0.94

initial

0.93

Activations Density 0.278%

phrases related to technical instructions or descriptions

specific characters or symbols, particularly variations of the letter 'l'

No Comments

No Known Activations