INDEX

Explanations

mentions of particular organizations or events

oai_token-act-pair · gpt-3.5-turbo

percentage values or numeric data within 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

 Morales

-0.70

 Melvin

-0.69

loo

-0.66

 Deity

-0.65

 Watson

-0.62

 Jacobs

-0.61

 Swanson

-0.60

 blinded

-0.59

 Hurt

-0.59

 inciner

-0.58

POSITIVE LOGITS

window

1.11

Loading

1.07

RAW

0.86

Topics

0.84

asters

0.84

âĵĺ

0.80

Posted

0.78

âĶĢâĶĢâĶĢâĶĢ

0.75

Trivia

0.75

clus

0.75

Activations Density 0.244%

mentions of particular organizations or events

percentage values or numeric data within the text

No Comments

No Known Activations