INDEX

Explanations

elements related to quantifiable results or metrics in a technical context

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

<eos>

-0.46

-0.45

kh

-0.45

 nắng

-0.45

temp

-0.44

yn

-0.44

だけでは

-0.43

 يتيمه

-0.43

ve

-0.43

pare

-0.42

POSITIVE LOGITS

 Exacts

1.01

parsedMessage

1.01

ReusableCell

1.00

 saites

0.89

 فريبيس

0.86

 otomatig

0.85

writeFieldEnd

0.82

DockStyle

0.82

Rohy

0.81

IntoConstraints

0.80

Activations Density 0.108%

elements related to quantifiable results or metrics in a technical context

No Comments

No Known Activations