INDEX

Explanations

phrases related to the Centers for Disease Control and Prevention (CDC)

oai_token-act-pair · gpt-3.5-turbo

references to various control agencies and their roles or actions

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

minecraft

-0.77

rawdownloadcloneembedreportprint

-0.77

 FANT

-0.70

forth

-0.70

Xi

-0.69

RESULTS

-0.67

resh

-0.67

FontSize

-0.66

former

-0.66

morrow

-0.66

POSITIVE LOGITS

itaire

0.86

ptives

0.77

 Devices

0.75

 Officers

0.73

stration

0.73

 Agency

0.73

 Centers

0.72

 procedures

0.72

 Procedures

0.72

eers

0.72

Activations Density 0.024%

phrases related to the Centers for Disease Control and Prevention (CDC)

references to various control agencies and their roles or actions

No Comments

No Known Activations