INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

references to people and places within various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

-0.92

anasia

-0.88

Netflix

-0.84

TPP

-0.75

atari

-0.71

Animation

-0.71

NSA

-0.70

iPhone

-0.70

USB

-0.68

andowski

-0.67

POSITIVE LOGITS

 town

1.09

 eastern

1.09

 southeastern

1.06

 northern

1.03

 northeastern

1.03

 downtown

1.02

 nearby

1.02

 southern

1.00

 southwestern

0.99

 northwestern

0.98

Activations Density 0.526%

proper nouns

references to people and places within various contexts

No Comments

No Known Activations