INDEX

Explanations

phrases related to expectations or obligations

oai_token-act-pair · gpt-3.5-turbo

normative or expected actions and behaviors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Finder

-0.76

Reviewer

-0.72

fortunately

-0.69

Reader

-0.67

 Appears

-0.66

lip

-0.64

aroo

-0.64

river

-0.63

DAQ

-0.62

clips

-0.61

POSITIVE LOGITS

 uphold

0.87

 behave

0.86

be

0.86

 compensate

0.84

 stick

0.83

ulhu

0.80

wered

0.80

 abide

0.80

 deflect

0.80

 steer

0.79

Activations Density 0.064%

phrases related to expectations or obligations

normative or expected actions and behaviors

No Comments

No Known Activations