INDEX

Explanations

words that are related to movement or change

oai_token-act-pair · gpt-3.5-turbo

instances of the letter "w"

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

 Lumpur

-0.84

 fracturing

-0.69

 headache

-0.68

hyde

-0.66

 unpre

-0.65

 responsibility

-0.65

 complicity

-0.65

 culp

-0.64

uate

-0.64

pora

-0.63

POSITIVE LOGITS

ither

1.22

atts

1.15

iggle

1.14

idd

1.14

irts

1.11

icket

1.10

ithering

1.10

ickets

1.09

atson

1.09

igg

1.07

Activations Density 0.016%

words that are related to movement or change

instances of the letter "w"

No Comments

No Known Activations