INDEX

Explanations

phrases related to accomplishments or completed actions

oai_token-act-pair · gpt-3.5-turbo

instances of significant accomplishments or notable actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Adds

-0.68

 ILCS

-0.65

%%%%

-0.63

 Recent

-0.62

Merit

-0.62

Adds

-0.60

 Recently

-0.59

ggles

-0.59

 Currently

-0.59

*/

-0.57

POSITIVE LOGITS

was

1.85

 consisted

1.71

was

1.65

 amounted

1.55

 mattered

1.55

 wasn

1.50

 depended

1.49

 remained

1.47

 belonged

1.45

 resembled

1.45

Activations Density 1.498%

phrases related to accomplishments or completed actions

instances of significant accomplishments or notable actions

No Comments

No Known Activations