INDEX

Explanations

words related to roles and responsibilities

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

 Citation

-0.69

ousse

-0.65

eele

-0.65

 landfall

-0.63

 referrals

-0.63

 collaborators

-0.63

 Publishers

-0.63

 Expend

-0.61

arthed

-0.61

Grab

-0.60

POSITIVE LOGITS

 role

0.78

 Mahjong

0.69

lot

0.69

role

0.68

 differently

0.68

 roles

0.67

andestine

0.64

 unfocusedRange

0.64

blers

0.63

 hardest

0.62

Activations Density 1.359%

words related to roles and responsibilities

No Comments

No Known Activations