INDEX

Explanations

words ending in "-om"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "om."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

++++++++++++++++

-0.68

 Actual

-0.64

LIST

-0.62

 nexus

-0.60

VO

-0.60

 overpower

-0.58

 pork

-0.58

 compuls

-0.58

 Veil

-0.56

actions

-0.56

POSITIVE LOGITS

orrow

1.14

obile

1.11

puter

1.11

otive

1.07

atoes

1.04

edia

1.04

useum

0.98

essage

0.97

merce

0.96

psons

0.96

Activations Density 0.022%

words ending in "-om"

instances of the word "om."

No Comments

No Known Activations