INDEX

Explanations

terms related to negative impacts and threats to systems or entities

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

داد

-0.55

айт

-0.46

 Intense

-0.44

 frumos

-0.44

 Schenk

-0.44

ouldering

-0.44

 Киє

-0.43

verständ

-0.42

roxene

-0.42

scp

-0.42

POSITIVE LOGITS

 snippetHide

1.23

Datuak

1.04

providedIn

0.98

PerformLayout

0.95

AddTagHelper

0.95

AnchorStyles

0.94

 Affecting

0.92

 harming

0.92

 affecting

0.86

 affect

0.86

Activations Density 0.373%

terms related to negative impacts and threats to systems or entities

No Comments

No Known Activations