INDEX

Explanations

phrases related to management, handling, addressing, and resolving various situations or problems

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

Fit

-0.55

 stripes

-0.55

ierre

-0.54

rium

-0.54

istries

-0.54

 Stability

-0.53

 formation

-0.53

 fortunes

-0.53

ajo

-0.52

ses

-0.52

POSITIVE LOGITS

by

1.33

BY

0.99

 anew

0.91

 separately

0.89

 elsewhere

0.84

 electronically

0.84

 aback

0.83

ynamic

0.83

 differently

0.82

 psychiat

0.81

Activations Density 1.608%

phrases related to management, handling, addressing, and resolving various situations or problems

No Comments

No Known Activations