INDEX

Explanations

instances where the word "apply" is used

oai_token-act-pair · gpt-3.5-turbo

instances of the word "apply" and its variations in different contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

etsk

-0.72

pod

-0.69

iger

-0.65

 artery

-0.64

audi

-0.63

;;;;;;;;

-0.63

lycer

-0.62

iHUD

-0.62

semb

-0.62

kered

-0.61

POSITIVE LOGITS

 waivers

0.77

onz

0.76

ILA

0.72

 waive

0.67

å§«

0.66

 compulsory

0.66

BILITY

0.66

emale

0.65

 COURT

0.65

 para

0.64

Activations Density 0.184%

instances where the word "apply" is used

instances of the word "apply" and its variations in different contexts

No Comments

No Known Activations