INDEX

Explanations

specific examples or instances within a context or scenario

oai_token-act-pair · gpt-3.5-turbo

phrases that introduce examples or case studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

inately

-0.80

essed

-0.77

ournal

-0.76

 priority

-0.70

istance

-0.68

ibles

-0.68

imately

-0.67

ief

-0.65

quire

-0.62

 accessory

-0.62

POSITIVE LOGITS

 illustrate

1.05

 Suppose

1.01

 illustrates

0.98

Example

0.98

 illustrating

0.95

 illust

0.91

example

0.90

 Example

0.90

 examples

0.80

Examples

0.78

Activations Density 0.231%

specific examples or instances within a context or scenario

phrases that introduce examples or case studies

No Comments

No Known Activations