INDEX

Explanations

phrases related to intelligence or cleverness

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

bered

-0.74

atern

-0.72

ICAN

-0.69

packages

-0.68

avez

-0.67

artifacts

-0.66

dates

-0.64

leased

-0.64

ETA

-0.63

avored

-0.62

POSITIVE LOGITS

 thinker

1.00

sonian

0.93

ctl

0.92

minded

0.85

smanship

0.84

 thinkers

0.84

guy

0.83

found

0.81

 smartest

0.79

ness

0.76

Activations Density 0.993%

phrases related to intelligence or cleverness

No Comments

No Known Activations