INDEX

Explanations

uncertain language or expressions indicating doubt or ambiguity

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

tic

-0.70

onite

-0.69

anti

-0.66

olis

-0.66

ngth

-0.64

elin

-0.62

tumblr

-0.62

Zone

-0.61

 Resist

-0.61

acca

-0.61

POSITIVE LOGITS

 specifics

1.20

 whether

1.11

how

1.07

why

1.06

 exactly

0.94

WHY

0.93

 whereabouts

0.91

 details

0.87

why

0.87

 precise

0.85

Activations Density 2.159%

uncertain language or expressions indicating doubt or ambiguity

No Comments

No Known Activations