INDEX

Explanations

words related to location or the act of being in a specific place

oai_token-act-pair · gpt-3.5-turbo

the word "reside" and its variations indicating places of residence or habitation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

raid

-0.84

nature

-0.76

pled

-0.75

air

-0.70

astical

-0.70

uyomi

-0.70

reg

-0.67

intendent

-0.67

expr

-0.65

stop

-0.65

POSITIVE LOGITS

 resides

0.91

RTX

0.87

 residing

0.87

 reside

0.84

DAQ

0.77

 resided

0.76

 housed

0.75

âĸ¬

0.73

uate

0.73

owship

0.72

Activations Density 0.011%

words related to location or the act of being in a specific place

the word "reside" and its variations indicating places of residence or habitation

No Comments

No Known Activations