INDEX

Explanations

instances where the word "same" is used in a sentence

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

references to similarity or equivalence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 12-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.hook_resid_post

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

å§«

-0.86

ensable

-0.81

lished

-0.80

opian

-0.79

ribut

-0.77

Äĩ

-0.76

kt

-0.75

better

-0.75

alf

-0.75

skirts

-0.73

POSITIVE LOGITS

 kinds

1.29

 thing

1.23

 sorts

1.17

 amount

1.15

 kind

1.09

 fate

1.04

 sort

1.02

 types

0.95

 type

0.94

 exact

0.92

Activations Density 0.109%

instances where the word "same" is used in a sentence

references to similarity or equivalence

No Comments

No Known Activations