INDEX

Explanations

phrases related to geographical locations or landmarks

oai_token-act-pair · gpt-3.5-turbo

the repeated use of the word "the" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

thood

-0.80

esome

-0.73

aldehyde

-0.73

lear

-0.69

amine

-0.69

upon

-0.69

nuts

-0.69

PLA

-0.67

epad

-0.66

ontent

-0.66

POSITIVE LOGITS

 outskirts

1.58

 shores

1.40

 edge

1.27

 coast

1.23

 slopes

1.19

 verge

1.16

 coasts

1.16

 brink

1.14

 banks

1.13

 shore

1.10

Activations Density 0.108%

phrases related to geographical locations or landmarks

the repeated use of the word "the" in various contexts

No Comments

No Known Activations