INDEX

Explanations

references to different strains, variations, or classifications within specific scientific or medical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

 Krie

-0.78



-0.78

 Figs

-0.76

Figs

-0.76

 Gleaner

-0.74

olahan

-0.74

Fig

-0.69

 décret

-0.68

хни

-0.67

{{\

-0.67

POSITIVE LOGITS

 Nand

0.90

GeneratedValue

0.89

 Kamb

0.88

AMB

0.84

ENT

0.84

Tink

0.83

DockStyle

0.82

ENT

0.81

Cindy

0.81

AnchorStyles

0.81

Activations Density 2.077%

references to different strains, variations, or classifications within specific scientific or medical contexts

No Comments

No Known Activations