INDEX

Explanations

words related to poetry

oai_token-act-pair · gpt-3.5-turbo

references to the letter "P" and variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

owship

-0.80

 EDITION

-0.71

 narrator

-0.70

ividual

-0.66

 Commodore

-0.65

worthiness

-0.64

lain

-0.64

 precision

-0.61

UAL

-0.60

 monitors

-0.59

POSITIVE LOGITS

pper

1.25

ppy

1.21

pping

1.15

ppel

1.10

pez

1.08

etry

1.06

pport

1.05

zzo

1.04

inters

1.04

ppo

1.03

Activations Density 0.025%

words related to poetry

references to the letter "P" and variations in different contexts

No Comments

No Known Activations