INDEX

Explanations

mentions of the word "Me" followed by a name or specific noun

oai_token-act-pair · gpt-3.5-turbo

the word "Me" in various contexts referring to individuals or personal experiences

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pole

-0.77

 totality

-0.72

 corners

-0.65

paralle

-0.62

 legality

-0.60

Closure

-0.59

 slic

-0.59

medium

-0.58

rift

-0.58

 chrome

-0.57

POSITIVE LOGITS

asuring

1.35

asured

1.25

asure

1.20

aning

1.15

asures

1.15

zzo

1.14

cca

1.12

ister

1.09

eker

1.05

adow

1.05

Activations Density 0.023%

mentions of the word "Me" followed by a name or specific noun

the word "Me" in various contexts referring to individuals or personal experiences

No Comments

No Known Activations