INDEX

Explanations

words related to activities involving planning or anticipation

oai_token-act-pair · gpt-3.5-turbo

words related to pre-existing conditions or states

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

loo

-0.78

 Slug

-0.75

 GOODMAN

-0.73

oice

-0.70

 Hearts

-0.70

ãĤ¼ãĤ¦ãĤ¹

-0.69

 Soup

-0.69

 Shack

-0.69

 Heights

-0.68

Ace

-0.68

POSITIVE LOGITS

requisites

1.21

occup

1.10

fecture

1.09

ceed

1.04

lude

1.03

req

1.03

cession

1.00

achers

0.99

hend

0.97

empt

0.96

Activations Density 0.017%

words related to activities involving planning or anticipation

words related to pre-existing conditions or states

No Comments

No Known Activations