INDEX

Explanations

mentions of specific governmental entities or authorities

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "government."

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

 gaps

-0.68

igmatic

-0.66

æĺ

-0.65

 expans

-0.65

picture

-0.63

paces

-0.63

iquid

-0.63

Spread

-0.62

 complicate

-0.62

 mosa

-0.61

POSITIVE LOGITS

ort

0.76

vice

0.75

stown

0.74

enance

0.72

igion

0.72

rium

0.71

 Excellence

0.70

sponsored

0.68

 course

0.68

orts

0.67

Activations Density 0.217%

mentions of specific governmental entities or authorities

occurrences of the word "government."

No Comments

No Known Activations