INDEX

Explanations

mentions or descriptions of penalties in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to penalties or punitive measures

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oir

-0.80

atters

-0.77

ership

-0.74

 Alive

-0.70

walking

-0.69

IFE

-0.69

rina

-0.69

geist

-0.69

ERN

-0.68

birth

-0.67

POSITIVE LOGITS

 penalties

1.28

 penalty

1.13

 levied

1.05

 sanction

0.99

 punishment

0.95

 punish

0.94

 punishments

0.94

 imposed

0.92

 undermin

0.91

 punished

0.90

Activations Density 0.009%

mentions or descriptions of penalties in various contexts

references to penalties or punitive measures

No Comments

No Known Activations