INDEX

Explanations

references to a specific word "Ark."

oai_token-act-pair · gpt-3.5-turbo

mentions of "Ark" and its various contexts 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 @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 diabetic

-0.76

 diabetes

-0.74

 sugars

-0.73

 caffeine

-0.73

 McMahon

-0.70

 Thai

-0.69

weeney

-0.68

uff

-0.68

 McMaster

-0.67

ugh

-0.65

POSITIVE LOGITS

Ark

4.16

Ark

2.92

Neb

1.21

 Arkansas

1.10

ARK

1.06

Ik

1.06

 Exodus

1.05

 Avatar

1.04

 Shroud

1.04

 Creation

1.03

Activations Density 0.015%

references to a specific word "Ark."

mentions of "Ark" and its various contexts throughout the text

No Comments

No Known Activations