INDEX

Explanations

mentions or contexts where the word "entire" is used to describe something

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "entire"

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

kick

-0.73

Blade

-0.65

bid

-0.64

asta

-0.64

po

-0.62

aminer

-0.61

ac

-0.60

inel

-0.60

ker

-0.60

cru

-0.58

POSITIVE LOGITS

heartedly

1.03

 entire

0.75

ciating

0.74

 Godd

0.72

oton

0.68

ODUCT

0.68

uania

0.68

 swat

0.68

foundland

0.68

hearted

0.67

Activations Density 0.016%

mentions or contexts where the word "entire" is used to describe something

occurrences of the word "entire"

No Comments

No Known Activations