INDEX

Explanations

terms related to legal and regulatory actions

oai_token-act-pair · gpt-3.5-turbo

references to awareness and emphasis on significant issues

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

fuck

-0.72

otti

-0.70

Evil

-0.67

 Nope

-0.65

atmeal

-0.65

iture

-0.64

 Somebody

-0.64

Yeah

-0.62

OTUS

-0.62

 yeah

-0.60

POSITIVE LOGITS

 concerns

1.20

 uncertainties

1.14

 shortcomings

1.13

 methodological

1.12

 disparities

1.07

 risks

1.02

 fears

1.02

 similarities

1.00

 differences

0.99

 longstanding

0.99

Activations Density 0.451%

terms related to legal and regulatory actions

references to awareness and emphasis on significant issues

No Comments

No Known Activations