INDEX

Explanations

phrases mentioning political parties

oai_token-act-pair · gpt-3.5-turbo

references to political parties and organizations

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

ËĪ

-0.84

gart

-0.77

nels

-0.70

netflix

-0.70

APTER

-0.70

sets

-0.69

asers

-0.67

ANS

-0.67

charges

-0.67

roo

-0.67

POSITIVE LOGITS

 Charity

0.81

 Shade

0.80

Day

0.76

 Garden

0.75

 Club

0.75

 Wife

0.74

Own

0.74

 Mercy

0.74

 Vengeance

0.73

 Choice

0.73

Activations Density 0.055%

phrases mentioning political parties

references to political parties and organizations

No Comments

No Known Activations