INDEX

Explanations

instances of the word "Perhaps" followed by a sentence

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

lete

-0.86

iya

-0.86

ament

-0.83

cies

-0.78

ombat

-0.75

ieve

-0.74

ieves

-0.73

ocaust

-0.73

atches

-0.73

cium

-0.72

POSITIVE LOGITS

 someday

1.18

 misunder

0.90

 unsurprisingly

0.88

 subconscious

0.86

 sensing

0.85

 underest

0.81

 underestimate

0.78

 overest

0.77

 somew

0.75

 exagger

0.74

Activations Density 1.139%

instances of the word "Perhaps" followed by a sentence

No Comments

No Known Activations