INDEX

Explanations

quantities or numerical values

oai_token-act-pair · gpt-3.5-turbo

the word "alone" in various contexts emphasizing isolation or singular occurrence

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

anty

-0.81

olid

-0.70

uay

-0.67

emies

-0.67

 Briggs

-0.67

aptic

-0.65

acies

-0.65

 alignment

-0.64

rigan

-0.63

eways

-0.62

POSITIVE LOGITS

 alone

0.77

 suffice

0.74

 accounted

0.68

SPONSORED

0.68

alone

0.68

plus

0.67

 admit

0.63

sen

0.63

åŃĲ

0.63

ighed

0.62

Activations Density 0.014%

quantities or numerical values

the word "alone" in various contexts emphasizing isolation or singular occurrence

No Comments

No Known Activations