INDEX

Explanations

references to criminal activity or investigations related to political figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 CreateTagHelper

-1.35

 doubtnut

-1.31

 purpoſe

-1.25

Efq

-1.23

 Majefty

-1.23

 Shakspeare

-1.21

 myſelf

-1.21

 Jefus

-1.20

 Anſ

-1.17

 ་་

-1.17

POSITIVE LOGITS

0.66

0.64

0.61

<eos>

0.61

in

0.58

0.57

0.56

 να

0.54

Activations Density 0.152%

references to criminal activity or investigations related to political figures

No Comments

No Known Activations