INDEX

Explanations

statements conveying observations or perceptions

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

pmwiki

-0.75

ItemTracker

-0.71

Contents

-0.68

Kin

-0.67

heres

-0.64

urdue

-0.64

ugal

-0.61

zinski

-0.60

Main

-0.59

BLE

-0.59

POSITIVE LOGITS

tale

0.99

ingly

0.76

 apart

0.69

ĵĺ

0.67

eth

0.65

eret

0.64

uyomi

0.63

 instinctively

0.63

 beforehand

0.63

 anecd

0.63

Activations Density 0.034%

statements conveying observations or perceptions

No Comments

No Known Activations