INDEX

Explanations

dates mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

mentions of specific dates and numerical values related to events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Genie

-0.67

 successive

-0.58

 broom

-0.57

 wand

-0.57

 favoured

-0.52

 secretaries

-0.52

 sterile

-0.52

 crown

-0.52

 mushroom

-0.51

 mole

-0.51

POSITIVE LOGITS

th

0.92

mber

0.76

thia

0.74

ember

0.74

eteenth

0.73

Reply

0.73

Loading

0.70

Ñı

0.68

venth

0.68

Activations Density 0.042%

dates mentioned in the text

mentions of specific dates and numerical values related to events

No Comments

No Known Activations