INDEX

Explanations

words related to preparing for or engaging in conflict or competition

oai_token-act-pair · gpt-3.5-turbo

gerunds and present participles related to action or engagement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.69

 sidel

-0.68

abyte

-0.67

bara

-0.67

article

-0.65

 unprotected

-0.63

 miscar

-0.63

 dangling

-0.62

 pursued

-0.62

dab

-0.62

POSITIVE LOGITS

 refreshed

0.81

 coats

0.77

ãĤ¤ãĥĪ

0.75

 Grounds

0.75

igue

0.74

éĹĺ

0.73

Ready

0.71

 Prepar

0.71

strap

0.71

arity

0.70

Activations Density 0.128%

words related to preparing for or engaging in conflict or competition

gerunds and present participles related to action or engagement

No Comments

No Known Activations