INDEX

Explanations

numbers related to statistics or metrics

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

numerical values or statistics related to events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 12-res-jb

Configuration

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

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_post

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 scrut

-0.76

 millenn

-0.72

 nomine

-0.72

 mayoral

-0.70

anooga

-0.69

 affordability

-0.68

 payoff

-0.67

agall

-0.66

 gloom

-0.66

 artisan

-0.64

POSITIVE LOGITS

 partName

1.26

1.21

1.20

1.18

1.17

1.16

Activations Density 0.057%

numbers related to statistics or metrics

numerical values or statistics related to events

No Comments

No Known Activations