INDEX

Explanations

specific terms related to technology and computing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 immemorial

-0.49

RenderAtEndOf

-0.47

 numberOfRows

-0.45

ersonal

-0.45

PhysRevD

-0.43

 Perkin

-0.43

 ostavi

-0.41

Created

-0.41

 estoppel

-0.41

SYNOPSIS

-0.41

POSITIVE LOGITS

UnusedPrivate

0.66

 iprot

0.62

 betweenstory

0.61

 ویکی‌پدیای

0.54

 interp

0.53

ContentAsync

0.52

 interrogated

0.52

ագրություններ

0.52

 doInBackground

0.52

 getIntent

0.51

Activations Density 0.128%

specific terms related to technology and computing

No Comments

No Known Activations