INDEX

Explanations

instances of punishment or disciplinary actions in a context

oai_token-act-pair · gpt-3.5-turbo

terms related to punishment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

gow

-0.81

soDeliveryDate

-0.81

Champ

-0.74

yip

-0.74

afety

-0.71

coe

-0.71

vironment

-0.70

itect

-0.70

eds

-0.70

ophe

-0.69

POSITIVE LOGITS

 harshly

1.09

 punished

0.89

 severely

0.85

 punish

0.84

 punishments

0.83

 punishment

0.81

 punishing

0.76

 unfairly

0.75

 penalties

0.75

GES

0.74

Activations Density 0.036%

instances of punishment or disciplinary actions in a context

terms related to punishment

No Comments

No Known Activations