INDEX

Explanations

phrases related to cause and effect

oai_token-act-pair · gpt-3.5-turbo

instances of the word "effect" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

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

 pigeon

-0.75

dig

-0.68

 Methodist

-0.62

croft

-0.60

apest

-0.59

zar

-0.59

 Timber

-0.58

Dud

-0.58

 Alto

-0.57

 Compet

-0.56

POSITIVE LOGITS

iveness

1.43

ual

1.17

ively

1.15

uated

1.15

uating

1.07

uation

1.04

uates

0.95

ually

0.95

ivation

0.90

uate

0.89

Activations Density 0.048%

phrases related to cause and effect

instances of the word "effect" and its variations

No Comments

No Known Activations