INDEX

Explanations

questions containing the word "know" and inquires about understanding or uncertainty

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_fs6144-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

6,144

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

naissance

-0.69

attery

-0.68

ishable

-0.66

ulas

-0.65

onite

-0.61

uilding

-0.61

oided

-0.60

Discussion

-0.59

Made

-0.59

izont

-0.59

POSITIVE LOGITS

 anymore

0.98

how

0.97

 whether

0.89

why

0.89

 exactly

0.85

 specifics

0.83

WHY

0.80

yet

0.79

 Dragonbound

0.78

yet

0.77

Activations Density 0.230%

questions containing the word "know" and inquires about understanding or uncertainty

No Comments

No Known Activations