INDEX

Explanations

dates or events represented in the format Day/Month

oai_token-act-pair · gpt-3.5-turbo

occurrences of a specific symbol or character throughout the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 constitu

-0.85

 imitation

-0.83

 disadvant

-0.83

 vulner

-0.74

 mathemat

-0.73

 carbohyd

-0.73

 blender

-0.72

 promoters

-0.72

 tangled

-0.68

 levers

-0.68

POSITIVE LOGITS

ï¸ı

1.21

ï¸

1.00

Ļ

0.91

İ

0.88

ħ

0.87

Ø§

0.85

å¥³

0.84

ATH

0.83

PT

0.81

ļ

0.81

Activations Density 0.458%

dates or events represented in the format Day/Month

occurrences of a specific symbol or character throughout the text

No Comments

No Known Activations