INDEX

Explanations

phrases indicating a comparison or a contrast between different entities

oai_token-act-pair · gpt-3.5-turbo

transitional phrases indicating contrasting or additional information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Defendants

-0.65

 Conversation

-0.61

 Families

-0.61

 Shack

-0.55

CY

-0.55

ancial

-0.54

 Definitions

-0.53

 Others

-0.52

 Presidents

-0.52

RTX

-0.52

POSITIVE LOGITS

.,

0.88

è£ħ

0.82

0.76

 insisted

0.71

,,

0.70

displayText

0.69

wrote

0.67

 insists

0.67

ignt

0.65

nsics

0.65

Activations Density 0.092%

phrases indicating a comparison or a contrast between different entities

transitional phrases indicating contrasting or additional information

No Comments

No Known Activations