INDEX

Explanations

mentions of the word "tenure"

oai_token-act-pair · gpt-3.5-turbo

references to the concept of tenure in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

afort

-0.67

ulsive

-0.67

Heart

-0.64

 Breast

-0.64

ortium

-0.63

 Stores

-0.62

 spontaneous

-0.61

kell

-0.61

ulsion

-0.60

mber

-0.60

POSITIVE LOGITS

 tenure

0.98

 reign

0.80

ahime

0.76

days

0.72

 spanning

0.68

enary

0.68

iod

0.67

era

0.67

 appointments

0.66

mates

0.66

Activations Density 0.014%

mentions of the word "tenure"

references to the concept of tenure in various contexts

No Comments

No Known Activations