INDEX

Explanations

phrases related to skepticism or skepticism towards official narratives, particularly involving political events or statements

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

zie

-0.83

 actionGroup

-0.82

ktop

-0.75

Interstitial

-0.74

ophon

-0.72

 downtime

-0.71

gallery

-0.70

 Gallery

-0.69

 Opportun

-0.65

 leisure

-0.65

POSITIVE LOGITS

 assertions

1.51

 assertion

1.37

 debunked

1.30

 claims

1.25

 hypotheses

1.23

 conjecture

1.22

 baseless

1.20

 falsehood

1.20

 claim

1.20

 validity

1.19

Activations Density 2.313%

phrases related to skepticism or skepticism towards official narratives, particularly involving political events or statements

No Comments

No Known Activations