INDEX

Explanations

concepts related to programming abstractions and details

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

manjaro

-0.55

 nyug

-0.49

RegistryLite

-0.47

 vermute

-0.45

 jednou

-0.44

 lipat

-0.44

 doble

-0.43

 vọng

-0.43

faßt

-0.43

ialmente

-0.42

POSITIVE LOGITS

 details

1.74

 detail

1.71

 specifics

1.64

details

1.62

 detailed

1.60

detailed

1.57

detail

1.57

 Detail

1.55

 Detailed

1.50

 Details

1.50

Activations Density 0.684%

concepts related to programming abstractions and details

No Comments

No Known Activations