INDEX

Explanations

references to specific individuals or entities within a narrative

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

EndContext

-0.74

GraphicsUnit

-0.74

 חיצוניים

-0.69

RenderAtEndOf

-0.63

AutoScale

-0.63

="@+

-0.63

+#+#

-0.57

 facie

-0.57

Worse

-0.54

saraba

-0.54

POSITIVE LOGITS

ENODEV

0.53

rited

0.52

 CURIAM

0.49

rungsseite

0.48

jsonwebtoken

0.47

weth

0.47

IDATE

0.47

Gemeinsame

0.47

lgari

0.46

proposition

0.46

Activations Density 0.240%

references to specific individuals or entities within a narrative

No Comments

No Known Activations