INDEX

Explanations

data analysis related terms

oai_token-act-pair · gpt-3.5-turbo

terms related to scientific research methodology and analysis

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

soDeliveryDate

-0.74

estate

-0.72

 trillions

-0.71

forums

-0.70

 Tant

-0.69

 Sovere

-0.69

 attracts

-0.68

 owes

-0.67

 swat

-0.66

tackle

-0.65

POSITIVE LOGITS

 randomized

0.93

 Subjects

0.89

 questionnaire

0.85

alyses

0.85

 Kaplan

0.85

 Participants

0.84

 validated

0.84

 analysed

0.84

 investigator

0.82

 ascertain

0.82

Activations Density 0.273%

data analysis related terms

terms related to scientific research methodology and analysis

No Comments

No Known Activations