INDEX

Explanations

terms related to modifications and alterations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 berhenti

-0.64

 câte

-0.59

 kří

-0.54

ByDefault

-0.54

allerie

-0.54

 Maximal

-0.53

 móds

-0.53

Объ

-0.52

Kariera

-0.52

 pengh

-0.52

POSITIVE LOGITS

 altering

1.35

 altered

1.32

 alterations

1.29

 alteration

1.26

 changes

1.24

 alters

1.22

 Changes

1.18

 modify

1.17

 modifying

1.17

 modifies

1.15

Activations Density 0.774%

terms related to modifications and alterations in various contexts

No Comments

No Known Activations