INDEX

Explanations

the word "probably" in the text

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

iya

-0.83

issy

-0.77

elight

-0.74

ible

-0.71

vers

-0.71

osi

-0.70

irl

-0.69

uctor

-0.69

lete

-0.69

aeus

-0.68

POSITIVE LOGITS

 overest

0.85

 misunder

0.83

 underestimate

0.80

 underest

0.80

 someday

0.79

won

0.77

 exagger

0.74

 underestimated

0.74

 outnumbered

0.73

 subconscious

0.71

Activations Density 0.049%

the word "probably" in the text

No Comments

No Known Activations