INDEX

Explanations

code snippets related to function calls and operations on collections

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

spo

-0.66

Ļ½

-0.65

 answ

-0.62

zers

-0.61

 artif

-0.60

clus

-0.60

 waste

-0.60

ku

-0.58

ãĥ¥

-0.57

front

-0.57

POSITIVE LOGITS

ãĥİ

0.81

 Frames

0.76

âķ

0.74

*.

0.68

 Committees

0.68

 Panc

0.64

eem

0.63

TPS

0.59

Limit

0.58

 Parables

0.58

Activations Density 0.706%

code snippets related to function calls and operations on collections

No Comments

No Known Activations