INDEX

Explanations

references to political figures and their alleged misconduct or corruption

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

(&

-0.68

®:

-0.64

!):

-0.61

®

-0.59

${

-0.59

\&

-0.58

-0.57

:${

-0.57

();

-0.56

::$

-0.55

POSITIVE LOGITS

 demnach

0.70

 amid

0.68

 zufolge

0.67

mln

0.63

－

0.63

MENAFN

0.62

 zvuky

0.59

 lawmaker

0.58

 विश्वसनीयता

0.57

 Sebab

0.57

Activations Density 0.101%

references to political figures and their alleged misconduct or corruption

No Comments

No Known Activations