INDEX

Explanations

words related to existence or disbelief in various contexts

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

hiba

-0.73

Thom

-0.64

edo

-0.64

Dro

-0.62

anche

-0.61

wer

-0.61

 broom

-0.61

Ĺ

-0.61

ilde

-0.60

ney

-0.60

POSITIVE LOGITS

entially

1.05

entials

0.96

places

0.83

 within

0.80

 existed

0.79

ential

0.78

nces

0.78

uate

0.73

 solely

0.73

 outside

0.72

Activations Density 0.037%

words related to existence or disbelief in various contexts

No Comments

No Known Activations