INDEX

Explanations

mentions of attitudes or beliefs

oai_token-act-pair · gpt-3.5-turbo

discussions and mentions surrounding the concept of "attitude."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

enegger

-0.96

icles

-0.87

oval

-0.76

icle

-0.72

amen

-0.72

idden

-0.71

dry

-0.67

ichen

-0.67

eri

-0.67

anz

-0.66

POSITIVE LOGITS

 toward

1.16

 attitude

1.16

 towards

1.13

 Towards

0.93

 attitudes

0.91

Tow

0.77

ysis

0.73

 stance

0.72

uation

0.72

 disposition

0.70

Activations Density 0.036%

mentions of attitudes or beliefs

discussions and mentions surrounding the concept of "attitude."

No Comments

No Known Activations