INDEX

Explanations

statements related to personal experiences and beliefs

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Contents

-0.72

icter

-0.72

itaire

-0.66

transform

-0.66

 Afgh

-0.63

*.

-0.62

 guiActiveUnfocused

-0.62

 actionGroup

-0.61

 comprom

-0.61

 incompet

-0.60

POSITIVE LOGITS

 laughs

0.89

 echoed

0.87

 Asked

0.85

Asked

0.83

 nods

0.81

 nodded

0.79

 Wiggins

0.77

 pauses

0.76

 chuckled

0.76

 smiles

0.76

Activations Density 0.611%

statements related to personal experiences and beliefs

No Comments

No Known Activations