INDEX

Explanations

phrases related to discussions and policies in various contexts

oai_token-act-pair · gpt-3.5-turbo

terms related to rational discourse and critical discussions surrounding policies and regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

netflix

-0.83

 ISBN

-0.72

 deserted

-0.64

 sounded

-0.62

 touched

-0.61

 Cosponsors

-0.61

 kissed

-0.60

inates

-0.60

 insulted

-0.60

cised

-0.60

POSITIVE LOGITS

 purposes

0.91

 endeavors

0.90

 survival

0.78

 overall

0.76

 formation

0.72

 longevity

0.71

 endeavor

0.70

 viability

0.70

 effectiveness

0.69

 behav

0.68

Activations Density 0.750%

phrases related to discussions and policies in various contexts

terms related to rational discourse and critical discussions surrounding policies and regulations

No Comments

No Known Activations