INDEX

Explanations

sequences of characters around symbols like punctuation or special characters

oai_token-act-pair · gpt-3.5-turbo

expressions of exasperation or frustration

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enegger

-0.82

ESSION

-0.78

lishes

-0.72

 omission

-0.67

 redist

-0.67

 segreg

-0.64

 prevailing

-0.64

ividual

-0.63

 Samoa

-0.63

ACP

-0.62

POSITIVE LOGITS

âĢķ

1.15

£

0.90

dro

0.89

¹

0.88

âĶĢ

0.80

âĻ

0.80

 âĢķ

0.80

º

0.78

½

0.78

¯

0.77

Activations Density 0.360%

sequences of characters around symbols like punctuation or special characters

expressions of exasperation or frustration

No Comments

No Known Activations