INDEX

Explanations

references to boilerplate code or templates in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

ensement

-0.72

वरण

-0.67

География

-0.66

 smrti

-0.65

 referenties

-0.65

שלום

-0.63

anasia

-0.62

 зданий

-0.61

 дії

-0.61

neté

-0.60

POSITIVE LOGITS

 ſche

0.90

LookAnd

0.86

 eſt

0.84

 ſta

0.74

 dinoss

0.74

neſs

0.71

ghijklmnop

0.71

 Afford

0.71

 ſtre

0.71

 trouva

0.70

Activations Density 3.150%

references to boilerplate code or templates in programming contexts

No Comments

No Known Activations