INDEX

Explanations

phrases or words related to the concept of human traits or characteristics

oai_token-act-pair · gpt-3.5-turbo

mentions of human-related concepts or attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 slice

-0.71

 launcher

-0.71

 blocks

-0.67

 Block

-0.66

 markup

-0.65

 Wall

-0.63

 cartels

-0.62

 Specialist

-0.62

AE

-0.61

 aligned

-0.61

POSITIVE LOGITS

hum

4.65

Hum

1.89

Hum

1.69

hum

1.28

HUM

1.23

hor

1.21

hus

1.14

odor

1.11

nat

1.10

hist

1.09

Activations Density 0.009%

phrases or words related to the concept of human traits or characteristics

mentions of human-related concepts or attributes

No Comments

No Known Activations