INDEX

Explanations

words related to video games and gaming activities

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

inx

-0.73

 politic

-0.68

iffe

-0.68

sie

-0.66

thening

-0.65

thens

-0.63

orship

-0.63

Osw

-0.62

orescent

-0.61

æĢ

-0.60

POSITIVE LOGITS

PLAY

1.09

cube

1.08

pad

1.07

play

1.05

wright

1.03

plays

0.99

 consoles

0.96

 Borderlands

0.94

keepers

0.86

plan

0.86

Activations Density 1.463%

words related to video games and gaming activities

No Comments

No Known Activations