INDEX

Explanations

assertions, claims, beliefs, understandings, reports, notes, and announcements made about specific events or situations

oai_token-act-pair · gpt-3.5-turbo

statements related to claims, beliefs, and expectations

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

ap

-0.77

avorite

-0.77

appings

-0.70

isode

-0.68

obos

-0.68

ROM

-0.67

ced

-0.66

izons

-0.66

picture

-0.66

quit

-0.65

POSITIVE LOGITS

 probable

0.73

 unanimously

0.69

 unclear

0.67

 timet

0.64

 Â¶

0.63

 raining

0.62

 incorrectly

0.62

 orally

0.62

 Engels

0.61

 incidentally

0.61

Activations Density 0.108%

assertions, claims, beliefs, understandings, reports, notes, and announcements made about specific events or situations

statements related to claims, beliefs, and expectations

No Comments

No Known Activations