INDEX

Explanations

phrases related to political movements or government actions

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

orts

-0.68

iple

-0.66

icable

-0.65

 commun

-0.62

ousel

-0.62

oyd

-0.60

...]

-0.59

ruck

-0.59

eks

-0.58

 level

-0.58

POSITIVE LOGITS

perhaps

1.22

especially

1.21

particularly

1.20

albeit

1.18

 namely

1.18

————

1.16

including

1.14

————————

1.09

_-

1.04

something

1.03

Activations Density 0.980%

phrases related to political movements or government actions

No Comments

No Known Activations