INDEX

Explanations

proper nouns related to Russian and Chinese individuals

oai_token-act-pair · gpt-3.5-turbo

mentions of specific individuals or entities, particularly those related to political or legal contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gart

-1.01

clusively

-0.81

usc

-0.77

aroo

-0.72

ikarp

-0.72

houses

-0.71

tailed

-0.70

cess

-0.70

itive

-0.70

ition

-0.69

POSITIVE LOGITS

Ð´

0.81

Ñı

0.73

izoph

0.71

py

0.70

;;;;;;;;;;;;

0.70

acket

0.69

zh

0.68

 correctness

0.67

pread

0.65

ÑĤ

0.65

Activations Density 0.014%

proper nouns related to Russian and Chinese individuals

mentions of specific individuals or entities, particularly those related to political or legal contexts

No Comments

No Known Activations