INDEX

Explanations

names of individuals and fictional characters.

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.58

-0.57

omorphic

-0.57

 Genius

-0.56

 Habit

-0.54

 Practices

-0.54

cle

-0.53

cffff

-0.52

bom

-0.52

oat

-0.52

POSITIVE LOGITS

ļéĨĴ

0.73

resp

0.66

ribute

0.66

================================================================

0.64

????????

0.63

amac

0.62

isoft

0.62

%%%%

0.61

ubric

0.60

anty

0.60

Activations Density 1.173%

names of individuals and fictional characters.

No Comments

No Known Activations