INDEX

Explanations

websites, movements, or organizations dedicated to a particular cause or theme

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a dedication or commitment to various causes or topics

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

epend

-0.78

 retracted

-0.72

 swayed

-0.72

loo

-0.69

 triggered

-0.63

isp

-0.62

 boarded

-0.62

met

-0.61

techn

-0.61

comings

-0.60

POSITIVE LOGITS

othy

0.81

 preserving

0.80

 Purpose

0.79

icial

0.71

 dedicate

0.69

 honoring

0.67

 Virtue

0.67

ternity

0.67

 maximize

0.67

 honor

0.66

Activations Density 0.077%

websites, movements, or organizations dedicated to a particular cause or theme

phrases indicating a dedication or commitment to various causes or topics

No Comments

No Known Activations