INDEX

Explanations

references to the name "Ban"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Ban" and variations thereof

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

IRE

-0.60

 ants

-0.58

trial

-0.58

 reckoning

-0.58

worldly

-0.55

stood

-0.55

 trough

-0.54

 governed

-0.54

 Reasons

-0.54

selves

-0.54

POSITIVE LOGITS

anas

1.29

ished

1.26

nered

1.23

quet

1.14

zai

1.14

ishing

1.10

ishment

1.10

aji

1.09

agher

1.06

ning

1.04

Activations Density 0.028%

references to the name "Ban"

mentions of the name "Ban" and variations thereof

No Comments

No Known Activations