INDEX

Explanations

references to specific neighborhoods and nomination mentions 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 @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 utafitiHapana

-0.94

 poética

-0.60

 păr

-0.60

 averaged

-0.60

 extrapolated

-0.60

zerland

-0.59

 impatience

-0.57

EPC

-0.56

 대한

-0.56

 Camus

-0.56

POSITIVE LOGITS

 nodded

0.97

nod

0.96

AutoresizingMask

0.85

Nod

0.84

Nomin

0.83

 nodding

0.83

featureID

0.82

 Вікі

0.79

 nominated

0.79

 nominate

0.77

Activations Density 0.058%

references to specific neighborhoods and nomination mentions in various contexts

No Comments

No Known Activations