INDEX

Explanations

instances where the document mentions initiating dialogue or discussions

oai_token-act-pair · gpt-3.5-turbo

words and phrases indicating intention or purpose

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

_.

-0.58

 disadvant

-0.57

 horizont

-0.57

anooga

-0.56

listed

-0.56

 nomine

-0.55

 costing

-0.53

 netted

-0.52

Required

-0.52

 lines

-0.52

POSITIVE LOGITS

ggles

0.97

asty

0.92

 avoid

0.91

 celebrate

0.89

 satisfy

0.87

 protect

0.87

 ensure

0.86

 relieve

0.86

 accompany

0.85

 maximize

0.85

Activations Density 0.409%

instances where the document mentions initiating dialogue or discussions

words and phrases indicating intention or purpose

No Comments

No Known Activations