INDEX

Explanations

complex justifications or explanations related to actions and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

 EconPapers

-0.75

 Pingback

-0.67

Tracce

-0.63

 AppCompatTheme

-0.59

 olympique

-0.56

 Saltar

-0.55

 HasFactory

-0.55

ủi

-0.55

DialogInterface

-0.55

 BoxDecoration

-0.54

POSITIVE LOGITS

apunov

0.67

]--;

0.61

UnusedPrivate

0.60

mangle

0.57

 bezeichneter

0.56

pecified

0.56

 tertentu

0.55

 resembling

0.53

withIdentifier

0.53

 nào

0.51

Activations Density 0.570%

complex justifications or explanations related to actions and events

No Comments

No Known Activations