INDEX

Explanations

mathematical terms or symbols indicative of equations and functions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

|}{$

-0.66

 konkre

-0.60

 vnto

-0.58

 قار

-0.57

 voic

-0.57

 Charlie

-0.55

aven

-0.55

 Gymnas

-0.55

LayoutPanel

-0.55

__[

-0.55

POSITIVE LOGITS

OrWhiteSpace

0.66

 onlyOwner

0.62

jdt

0.62

EDEFAULT

0.61

enumi

0.60

oxone

0.58

GraphicsUnit

0.58

bootstrapcdn

0.57

walde

0.56

 balanceOf

0.56

Activations Density 0.541%

mathematical terms or symbols indicative of equations and functions

No Comments

No Known Activations