INDEX

Explanations

terms related to measurement, documentation, and refinement processes 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 @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sélectionnés

-0.48

 concernés

-0.47

ással

-0.47

 esetben

-0.46

 ilmu

-0.45

Compiled

-0.45

 humanidade

-0.44

발

-0.43

 marquées

-0.43

важа

-0.43

POSITIVE LOGITS

 متعلقه

0.76

 easily

0.69

easily

0.69

astify

0.68

ագրություններ

0.67

SocketAddress

0.66

wpi

0.64

脚注の使い方

0.64

**/

0.64

weza

0.64

Activations Density 0.394%

terms related to measurement, documentation, and refinement processes in various contexts

No Comments

No Known Activations