INDEX

Explanations

sequential actions or processes described in "step-by-step" format

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

 noDo

-0.46

jkl

-0.46

HideFlags

-0.44

 contracted

-0.44

:][

-0.43

שרה

-0.42

ையில்

-0.42

 groen

-0.40

adhyay

-0.40

書館

-0.39

POSITIVE LOGITS

Parcelize

0.72

iprot

0.70

ுக்கு

0.69

شوف

0.67

DeleteBehavior

0.67

IContainer

0.66

 stringBy

0.66

Geplaatst

0.66

byg

0.66

 CURLOPT

0.65

Activations Density 0.229%

sequential actions or processes described in "step-by-step" format

No Comments

No Known Activations