INDEX

Explanations

dates in various formats

oai_token-act-pair · gpt-3.5-turbo

dates or times mentioned in the text

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

opic

-0.73

 glim

-0.73

 princ

-0.70

 predec

-0.67

 neighb

-0.66

 ingred

-0.66

 cumbers

-0.63

bom

-0.62

 marqu

-0.60

 liner

-0.60

POSITIVE LOGITS

 âĶľ

0.86

 onwards

0.84

edin

0.83

flower

0.79

0.78

ois

0.75

0.73

0.72

0.71

Activations Density 0.048%

dates in various formats

dates or times mentioned in the text

No Comments

No Known Activations