INDEX

Explanations

the word "hop" occurring in various contexts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "hop" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Downloadha

-0.86

 payable

-0.79

ateral

-0.79

©¶æ

-0.72

ISE

-0.67

 confir

-0.66

 Printed

-0.64

ISION

-0.64

ettings

-0.63

cester

-0.62

POSITIVE LOGITS

Hop

1.42

hop

1.41

Hop

1.11

hop

1.05

 hops

1.01

eful

0.98

otle

0.96

efully

0.92

along

0.81

 hopping

0.79

Activations Density 0.008%

the word "hop" occurring in various contexts

instances of the word "hop" and its variations

No Comments

No Known Activations