INDEX

Explanations

references to genes and gene-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 nakalista

-0.71

 مشين

-0.66

 crossorigin

-0.65

thâu

-0.63

createCanvas

-0.61

odiment

-0.61

AndEndTag

-0.61

endphp

-0.60

 möjligt

-0.58

didSet

-0.57

POSITIVE LOGITS

 ffilmiau

0.67

 Lorca

0.64

########.

0.62

Bronnen

0.61

 appuntamento

0.61

GSP

0.60

GSC

0.60

BagLayout

0.58

UserScript

0.58

 tidings

0.57

Activations Density 1.384%

references to genes and gene-related terms

No Comments

No Known Activations