INDEX

Explanations

instances where someone is watching or watched something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "watching" and its variations

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

interstitial

-0.89

 congr

-0.77

ctrl

-0.74

esan

-0.72

enture

-0.70

inia

-0.69

ãĥ´

-0.68

eno

-0.66

ascal

-0.65

 lettuce

-0.65

POSITIVE LOGITS

 Watching

1.13

dogs

1.09

tower

1.03

dog

1.03

 watching

0.93

 helpless

0.90

 watched

0.83

 closely

0.82

 passively

0.80

watching

0.78

Activations Density 0.029%

instances where someone is watching or watched something

instances of the word "watching" and its variations

No Comments

No Known Activations