INDEX

Explanations

dates mentioned in the format: month, year

oai_token-act-pair · gpt-3.5-turbo

specific dates and months from different years

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 tremend

-0.75

 exting

-0.72

 corrid

-0.72

-0.71

 princ

-0.70

 newcom

-0.70

ï¸

-0.70

awaru

-0.68

intendent

-0.68

bart

-0.67

POSITIVE LOGITS

 Outlook

0.60

 Tutorial

0.59

 Gram

0.58

 chances

0.56

 Category

0.55

 Documentation

0.55

AVG

0.54

 Meteor

0.54

 Installation

0.54

 Setup

0.53

Activations Density 0.094%

dates mentioned in the format: month, year

specific dates and months from different years

No Comments

No Known Activations