INDEX

Explanations

the word "act" or words related to acting, such as "actor" or "acted"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "act" or its variations in different contexts

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

Rou

-0.74

 pinned

-0.67

 blinded

-0.67

bun

-0.66

Pru

-0.63

 prof

-0.61

dun

-0.60

 overl

-0.60

Nou

-0.59

 overfl

-0.58

POSITIVE LOGITS

act

4.49

acts

2.41

actor

2.39

acted

2.22

ACT

2.13

actic

2.09

acting

2.08

acter

1.68

action

1.62

Act

1.56

Activations Density 0.008%

the word "act" or words related to acting, such as "actor" or "acted"

occurrences of the word "act" or its variations in different contexts

No Comments

No Known Activations