INDEX

Explanations

terms related to robotics or robotic technology

oai_token-act-pair · gpt-3.5-turbo

terms related to robotics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

adr

-0.73

AIDS

-0.72

 Finder

-0.69

ires

-0.69

iyah

-0.68

Recommend

-0.68

tex

-0.68

oot

-0.68

rees

-0.67

ulhu

-0.67

POSITIVE LOGITS

 robotic

1.15

 robotics

0.84

¥ŀ

0.80

ĸļ

0.80

 prost

0.79

 gobl

0.78

 automation

0.76

 braking

0.75

isted

0.74

 limb

0.73

Activations Density 0.005%

terms related to robotics or robotic technology

terms related to robotics

No Comments

No Known Activations