INDEX

Explanations

key terms related to biological functions and classifications

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

relations or correspondence

np_acts-logits-general · gemini-2.0-flash

corresponding descriptions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 ostavi

-0.63

__(/*!

-0.58

Jeografia

-0.55

 AssemblyProduct

-0.55

IUrlHelper

-0.50

expandindo

-0.49

Jokes

-0.46

userdata

-0.46

SenderId

-0.45

idosis

-0.45

POSITIVE LOGITS

 corresponding

1.04

corresponding

0.87

 respective

0.87

 each

0.81

对应

0.81

 corrispond

0.81

 jeweiligen

0.78

 nahilalakip

0.78

 correspond

0.76

 descriptions

0.76

Activations Density 0.705%

key terms related to biological functions and classifications

relations or correspondence

corresponding descriptions

No Comments

No Known Activations