INDEX

Explanations

phrases and statements regarding interpretation and clarification of meaning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

TypedDataSet

-0.91

 يتيمه

-0.78

endphp

-0.77

 poffe

-0.76

UnsafeEnabled

-0.75

 pleaſure

-0.70

 occaf

-0.70

SPATH

-0.69

 ſeveral

-0.69

 reafon

-0.68

POSITIVE LOGITS

 meant

0.65

 meaning

0.62

 منظور

0.61

 gyhoeddwyd

0.59

WriteTagHelper

0.58

 Specifically

0.58

 specifically

0.57

 maksud

0.55

 bedoeld

0.54

 mean

0.54

Activations Density 0.308%

phrases and statements regarding interpretation and clarification of meaning

No Comments

No Known Activations