INDEX

Explanations

phrases related to legal or political actions

oai_token-act-pair · gpt-3.5-turbo

punctuation marks and special characters in the text

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

erest

-0.77

 nood

-0.65

 ling

-0.64

 comfort

-0.63

 mercy

-0.63

earch

-0.62

 level

-0.62

 mail

-0.62

rocal

-0.61

 mall

-0.61

POSITIVE LOGITS

including

1.16

perhaps

1.11

particularly

1.08

something

1.05

which

1.04

meaning

1.03

possibly

1.02

albeit

1.01

whose

0.96

especially

0.96

Activations Density 0.176%

phrases related to legal or political actions

punctuation marks and special characters in the text

No Comments

No Known Activations