INDEX

Explanations

mentions of the word "well" followed by a number rating

oai_token-act-pair · gpt-3.5-turbo

the adverb "well."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ategory

-0.62

TAG

-0.59

 generated

-0.58

 torn

-0.58

Ts

-0.58

 glam

-0.58

 finance

-0.57

 style

-0.57

 pric

-0.57

 generation

-0.56

POSITIVE LOGITS

well

4.61

Well

1.48

 well

1.32

 Well

1.27

hey

1.19

way

1.17

wait

1.11

we

1.06

worth

1.02

stable

1.01

Activations Density 0.010%

mentions of the word "well" followed by a number rating

the adverb "well."

No Comments

No Known Activations