INDEX

Explanations

phrases related to policies or actions being put in place to address various issues or challenges

oai_token-act-pair · gpt-3.5-turbo

phrases related to establishing systems or frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

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

mania

-0.83

ogi

-0.80

ishi

-0.79

lez

-0.76

STER

-0.75

iddle

-0.73

Enjoy

-0.73

anders

-0.71

ubi

-0.70

fest

-0.69

POSITIVE LOGITS

 safeguards

1.48

 guidelines

1.32

 incentives

1.22

 adequate

1.19

 mechanisms

1.18

 guidance

1.17

 corrective

1.14

 appropriate

1.13

 penalties

1.12

 protections

1.10

Activations Density 0.526%

phrases related to policies or actions being put in place to address various issues or challenges

phrases related to establishing systems or frameworks

No Comments

No Known Activations