INDEX

Explanations

phrases relating to specific activities or accomplishments, potentially in a narrative context

oai_token-act-pair · gpt-3.5-turbo

instances of a specific character or possibly a recurring theme associated with a character

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 guiActiveUnfocused

-0.90

 Palest

-0.67

 hors

-0.66

Jed

-0.65

 Izan

-0.64

 Kirin

-0.64

 fortun

-0.63

 scattering

-0.62

 Lovely

-0.61

 Droid

-0.61

POSITIVE LOGITS

£

0.93

should

0.89

\'

0.86

said

0.83

could

0.83

agree

0.82

Â§

0.80

Â¯

0.79

Pg

0.79

¹

0.79

Activations Density 0.311%

phrases relating to specific activities or accomplishments, potentially in a narrative context

instances of a specific character or possibly a recurring theme associated with a character

No Comments

No Known Activations