INDEX

Explanations

references to studies or research indicating a need for further investigation or action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 resourceCulture

-0.84

 springfox

-0.71

 Winaray

-0.64

 ComVisible

-0.62

Климат

-0.62

ⓧ

-0.59

сылкі

-0.59

ThroughAttribute

-0.58

 initComponents

-0.56

KeySpec

-0.55

POSITIVE LOGITS

 determine

1.27

 assess

1.00

 understand

0.97

 measure

0.95

determine

0.94

 Determine

0.89

 evaluate

0.87

 estimate

0.86

 ascertain

0.85

 investigate

0.85

Activations Density 0.685%

references to studies or research indicating a need for further investigation or action

No Comments

No Known Activations