INDEX

Explanations

mentions of walls in the context of politics

oai_token-act-pair · gpt-3.5-turbo

references to a "wall," particularly in the context of physical barriers or political promises

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

Gene

-0.77

forward

-0.68

×ķ

-0.67

lihood

-0.66

amate

-0.64

Pacific

-0.64

munition

-0.62

lishing

-0.62

ria

-0.62

ensation

-0.61

POSITIVE LOGITS

abies

1.18

papers

1.11

aby

1.06

 wall

0.91

 wart

0.86

clock

0.86

top

0.83

 thickness

0.81

 walls

0.81

 separating

0.81

Activations Density 0.012%

mentions of walls in the context of politics

references to a "wall," particularly in the context of physical barriers or political promises

No Comments

No Known Activations