INDEX

Explanations

mentions of introducing or being introduced to something or someone

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

 msec

-0.65

falls

-0.63

fall

-0.63

boy

-0.63

elf

-0.61

unker

-0.61

die

-0.59

halla

-0.58

wal

-0.58

ache

-0.58

POSITIVE LOGITS

urated

0.77

 INTO

0.74

prises

0.74

tainment

0.74

into

0.72

introdu

0.71

prise

0.70

tion

0.69

 anew

0.68

taining

0.67

Activations Density 0.041%

mentions of introducing or being introduced to something or someone

No Comments

No Known Activations