INDEX

Explanations

instances of text related to entering a location or position

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "enter" and related phrases that involve entering spaces or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

onne

-0.86

worn

-0.70

otin

-0.68

killers

-0.68

arians

-0.64

kick

-0.64

uren

-0.64

anan

-0.63

rex

-0.63

mates

-0.63

POSITIVE LOGITS

 fray

1.52

 realm

1.01

 room

0.98

 courtroom

0.97

 arena

0.95

 trance

0.95

 gates

0.95

 labyrinth

0.94

 equation

0.93

 cockpit

0.89

Activations Density 0.152%

instances of text related to entering a location or position

occurrences of the word "enter" and related phrases that involve entering spaces or entities

No Comments

No Known Activations