INDEX

Explanations

mentions of proper names, potentially related to interviews or profiles

oai_token-act-pair · gpt-3.5-turbo

the letter "G" at the beginning of various words or phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ĸļ

-0.75

 derail

-0.62

 compr

-0.62

 Mellon

-0.58

 parted

-0.58

 reprodu

-0.58

htt

-0.58

puter

-0.57

 craw

-0.57

terday

-0.56

POSITIVE LOGITS

roups

1.35

raphic

1.30

reetings

1.22

ourmet

1.18

ossip

1.17

reens

1.16

irlfriend

1.15

iants

1.15

AMES

1.14

uild

1.13

Activations Density 0.048%

mentions of proper names, potentially related to interviews or profiles

the letter "G" at the beginning of various words or phrases

No Comments

No Known Activations