INDEX

Explanations

JavaScript code snippets with specific patterns related to advertising or image display, such as inserting thumbnails or galleries

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

'"

-0.58

SUM

-0.58

pmwiki

-0.57

saf

-0.57

 ..............

-0.57

 Died

-0.55

[+

-0.53

chin

-0.53

'>

-0.53

nikov

-0.52

POSITIVE LOGITS

 payday

0.70

ubi

0.69

anooga

0.63

 commuting

0.62

 respectively

0.62

awaru

0.61

undai

0.60

aido

0.60

ģ«

0.60

 Lerner

0.60

Activations Density 0.024%

JavaScript code snippets with specific patterns related to advertising or image display, such as inserting thumbnails or galleries

No Comments

No Known Activations