INDEX

Explanations

quantitative expressions and references to amounts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PhysRev

-0.69

Des

-0.67

PhysRevLett

-0.60

 EventArgs

-0.59

Des

-0.58

zydent

-0.55

URBANA

-0.54

 being

-0.54

brak

-0.53

өз

-0.52

POSITIVE LOGITS

 disambiguazione

0.78

AddTagHelper

0.74

 Infórmanos

0.59

atihan

0.55

**/

0.54

RUnlock

0.54

 vägen

0.52

AndEndTag

0.51

tvguidetime

0.51

سمبر

0.50

Activations Density 0.577%

quantitative expressions and references to amounts

No Comments

No Known Activations