INDEX

Explanations

proper nouns, likely focusing on company names such as "DreamWorks" and "Steamworks"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "Works" 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Cath

-0.71

 cardinal

-0.63

 Adin

-0.62

 priests

-0.61

 Legions

-0.60

 solitary

-0.59

roy

-0.58

judicial

-0.58

ANA

-0.58

...]

-0.58

POSITIVE LOGITS

hops

1.65

pace

1.30

paces

1.21

hirt

1.09

works

1.05

heet

1.02

Works

0.99

hift

0.92

dayName

0.92

ername

0.89

Activations Density 0.016%

proper nouns, likely focusing on company names such as "DreamWorks" and "Steamworks"

occurrences of the term "Works" in various contexts

No Comments

No Known Activations