INDEX

Explanations

mentions of people providing care or assistance in different scenarios

oai_token-act-pair · gpt-3.5-turbo

references to roles and responsibilities associated with public service and safety

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

ocry

-0.68

 champagne

-0.66

onyms

-0.66

æĺ

-0.64

eton

-0.64

çīĪ

-0.63

 Wine

-0.63

intent

-0.62

ceivable

-0.62

ABV

-0.62

POSITIVE LOGITS

 duties

1.05

 overseeing

0.98

 guarding

0.98

 protecting

0.92

 assisting

0.90

 duty

0.89

 Assist

0.86

 guiding

0.83

keeping

0.81

 aids

0.81

Activations Density 0.671%

mentions of people providing care or assistance in different scenarios

references to roles and responsibilities associated with public service and safety

No Comments

No Known Activations