INDEX

Explanations

comparisons or evaluations involving various measurements or attributes

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_fs768-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

768

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

edy

-0.84

ioxide

-0.79

cffffcc

-0.76

ĸļ

-0.73

arkable

-0.63

ATOR

-0.63

elman

-0.63

quel

-0.62

cellaneous

-0.61

 guiActiveUn

-0.61

POSITIVE LOGITS

 they

0.92

he

0.75

 THEY

0.73

we

0.71

she

0.71

 constitutes

0.69

soever

0.69

they

0.68

you

0.67

it

0.66

Activations Density 3.881%

comparisons or evaluations involving various measurements or attributes

No Comments

No Known Activations