INDEX

Explanations

words indicating time references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

]<<"

-0.66

 HttpResponse

-0.65

Atentamente

-0.65

IsPostBack

-0.63

ソッド

-0.62

__':

-0.61

 DialogResult

-0.61

LookAnd

-0.61

fromnode

-0.60

AsUp

-0.59

POSITIVE LOGITS

 AssemblyTitle

0.74

concel

0.63

 distanciation

0.56

covite

0.54

 Moun

0.53

 entiendo

0.53

WebVitals

0.52

 curious

0.50

lidene

0.50

 Optic

0.48

Activations Density 0.081%

words indicating time references

No Comments

No Known Activations