INDEX

Explanations

product or service ratings

oai_token-act-pair · gpt-3.5-turbo

phrases related to ratings or evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Cheong

-0.76

adra

-0.76

natureconservancy

-0.74

externalActionCode

-0.74

Nou

-0.71

ouf

-0.71

vous

-0.70

ettlement

-0.69

pled

-0.69

alter

-0.68

POSITIVE LOGITS

Rated

0.92

 rated

0.83

 Rated

0.82

rated

0.78

rating

0.77

aily

0.73

ħĭ

0.68

 lumber

0.67

inois

0.67

 livest

0.66

Activations Density 0.030%

product or service ratings

phrases related to ratings or evaluations

No Comments

No Known Activations