INDEX

Explanations

references to the name "John"

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

 perus

-0.58

 diferencial

-0.55

newtheorem

-0.53

bukkit

-0.52

ResponseEntity

-0.52

దు

-0.52

tte

-0.51

 versa

-0.51

illotine

-0.51

 termica

-0.51

POSITIVE LOGITS

athan

1.08

fjspx

0.83

InitVars

0.82

Doe

0.75

nys

0.75

athon

0.74

 Deere

0.73

ATHAN

0.71

__(/*!

0.69

Doe

0.67

Activations Density 0.068%

references to the name "John"

No Comments

No Known Activations