INDEX

Explanations

names or terms related to individuals or characters, potentially from different contexts or works

oai_token-act-pair · gpt-3.5-turbo

the repeated occurrences of the character "u"

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 skelet

-0.71

 horizont

-0.70

=-=-

-0.65

 Payton

-0.63

-0.60

 incompet

-0.60

 Compass

-0.60

 SERV

-0.59

 initials

-0.58

POSITIVE LOGITS

cca

1.33

pport

1.18

itton

1.09

ccess

1.09

seless

1.08

pta

1.07

cius

1.05

igi

1.03

isine

0.99

hiro

0.99

Activations Density 0.054%

names or terms related to individuals or characters, potentially from different contexts or works

the repeated occurrences of the character "u"

No Comments

No Known Activations