INDEX

Explanations

verbs or phrases related to showing proof of something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "demonstrate" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

zone

-0.74

ole

-0.71

 Mistress

-0.67

 Returning

-0.66

lake

-0.65

alez

-0.65

etheless

-0.63

 dwelling

-0.62

pop

-0.61

query

-0.60

POSITIVE LOGITS

=>

0.81

 demonstrates

0.81

anooga

0.80

 demonstrating

0.79

GoldMagikarp

0.78

 feats

0.77

 demonstrations

0.75

issance

0.75

 demonstration

0.74

 demonstr

0.73

Activations Density 0.021%

verbs or phrases related to showing proof of something

instances of the word "demonstrate" and its variations

No Comments

No Known Activations