INDEX

Explanations

specific mentions or references to the contents of things

oai_token-act-pair · gpt-3.5-turbo

references to the term "contents" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Äĩ

-0.76

roads

-0.76

ansson

-0.76

verbs

-0.68

 Humph

-0.65

paralle

-0.62

ILLE

-0.62

lease

-0.62

arms

-0.61

orks

-0.60

POSITIVE LOGITS

 contents

1.00

matter

0.93

 thereof

0.86

ious

0.84

iveness

0.79

ions

0.79

 Contents

0.77

paces

0.75

 drawer

0.74

 therein

0.69

Activations Density 0.035%

specific mentions or references to the contents of things

references to the term "contents" in various contexts

No Comments

No Known Activations