INDEX

Explanations

content related to political manipulation and conspiracy theories

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ArgsConstructor

-0.59

 HasFactory

-0.53

Tracce

-0.49

 Broth

-0.48

awtextra

-0.47

 IndexPath

-0.47

 Scip

-0.45

_));

-0.45

 holster

-0.44

(":");

-0.43

POSITIVE LOGITS

RegressionTest

0.91

 للمعارف

0.65

 attacks

0.58

 AssemblyCulture

0.58

 Wikimedijinoj

0.57

///</

0.56

jooq

0.55

Література

0.55

nî

0.55

 destructive

0.54

Activations Density 0.537%

content related to political manipulation and conspiracy theories

No Comments

No Known Activations