INDEX

Explanations

numbers and specific quantitative information

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

icz

-0.67

Kar

-0.67

lance

-0.65

ĵ

-0.65

Smy

-0.63

Sz

-0.63

ighter

-0.63

 Weir

-0.62

 Akin

-0.61

 Quantity

-0.61

POSITIVE LOGITS

 categories

0.91

 finalists

0.91

 factors

0.83

 contenders

0.81

arios

0.76

 possibilities

0.76

 pieces

0.76

 scenarios

0.76

 choices

0.75

 possible

0.75

Activations Density 0.446%

numbers and specific quantitative information

No Comments

No Known Activations