INDEX

Explanations

proper nouns related to political figures and organizations

oai_token-act-pair · gpt-3.5-turbo

acronyms and unique identifiers related to organizations or people

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

rawdownloadcloneembedreportprint

-0.80

requires

-0.72

falls

-0.69

rw

-0.66

erity

-0.66

hess

-0.65

Äĩ

-0.65

alli

-0.64

hens

-0.63

thur

-0.63

POSITIVE LOGITS

 mathemat

0.73

×©

0.64

ãĤ¼

0.62

 livest

0.62

 charism

0.61

GROUP

0.61

 Kong

0.61

 therap

0.60

 Walton

0.60

Ø¯

0.60

Activations Density 0.386%

proper nouns related to political figures and organizations

acronyms and unique identifiers related to organizations or people

No Comments

No Known Activations