INDEX

Explanations

phrases or words related to "Ins," potentially referring to an organization or concept

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Ins" and accompanying variations in context, likely related to a specific organization or entity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

âĢ¢âĢ¢

-0.77

llan

-0.74

ries

-0.70

 Puzzles

-0.67

 litter

-0.66

RTX

-0.66

theless

-0.65

 Thumbnails

-0.65

ãĥ£

-0.62

 Carbuncle

-0.61

POSITIVE LOGITS

urrection

1.29

omnia

1.29

ights

1.29

urance

1.25

ufficient

1.23

ulin

1.16

iders

1.12

idious

1.10

ensitive

1.07

pection

1.03

Activations Density 0.025%

phrases or words related to "Ins," potentially referring to an organization or concept

instances of the word "Ins" and accompanying variations in context, likely related to a specific organization or entity

No Comments

No Known Activations