INDEX

Explanations

words related to punishment or retribution

oai_token-act-pair · gpt-3.5-turbo

references to punishment and its implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

sonian

-0.91

coe

-0.90

gow

-0.90

soDeliveryDate

-0.80

roots

-0.76

ophe

-0.74

zyme

-0.73

ortment

-0.72

ouf

-0.71

eds

-0.71

POSITIVE LOGITS

 harshly

0.92

 punished

0.91

 punishments

0.86

 inflicted

0.86

 punishment

0.83

 severely

0.81

 punish

0.79

 tant

0.76

 vanquished

0.73

 humiliation

0.73

Activations Density 0.033%

words related to punishment or retribution

references to punishment and its implications

No Comments

No Known Activations