INDEX

Explanations

references to the name "Mullen"

oai_token-act-pair · gpt-3.5-turbo

the repeated mention of the name "Mullen" and variations of it

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Scient

-0.66

WTO

-0.64

 Veronica

-0.64

 Constantin

-0.63

chnology

-0.63

 SYSTEM

-0.60

UU

-0.60

 OECD

-0.60

 Legislative

-0.60

 Whole

-0.58

POSITIVE LOGITS

igans

1.27

igan

1.23

aroo

1.15

ahs

1.08

indal

0.98

edin

0.97

ules

0.93

aby

0.92

inx

0.91

htar

0.89

Activations Density 0.010%

references to the name "Mullen"

the repeated mention of the name "Mullen" and variations of it

No Comments

No Known Activations