INDEX

Explanations

mentions of influential figures and their roles in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 disambiguazione

-0.88

]")]

-0.83

 برانيه

-0.83

Autoritní

-0.83

AddTagHelper

-0.81

findpost

-0.75

 iprot

-0.74

 AssemblyCulture

-0.73

 للاسماء

-0.70

MessageOf

-0.70

POSITIVE LOGITS

 former

0.59

former

0.57

ytt

0.56

Tat

0.51

겸

0.51

 AssemblyTitle

0.51

chauff

0.50

 prejudicial

0.49

 tevens

0.49

룡

0.47

Activations Density 0.132%

mentions of influential figures and their roles in various contexts

No Comments

No Known Activations