INDEX

Explanations

references to physical gestures or movements related to arms and hands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Tycoon

-0.79

ãĤ©

-0.76

 disinformation

-0.71

ontent

-0.71

VW

-0.67

 Calls

-0.66

 redundancy

-0.64

 Deaths

-0.63

ainment

-0.61

Sov

-0.61

POSITIVE LOGITS

 clasp

1.09

creen

0.96

stretched

0.93

 tightly

0.86

 palms

0.85

 stretched

0.85

 wrapped

0.84

 gripped

0.83

 paws

0.83

 clutching

0.81

Activations Density 0.019%

references to physical gestures or movements related to arms and hands

No Comments

No Known Activations