INDEX

Explanations

terms and concepts related to mathematical or statistical analysis and verification processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 avoient

-0.91

 feroit

-0.91

 houſe

-0.90

{},

-0.90

 pouvoit

-0.89

 pleaſure

-0.89

 reaſon

-0.88

 ſon

-0.87

 figliu

-0.87

 Jefus

-0.86

POSITIVE LOGITS

↵

0.63

 AttributeSet

0.57

 limit

0.56

 محفوظة

0.54

</blockquote>

0.54

0.53

Gemeinsame

0.53

0.51

↵↵

0.49

Of

0.49

Activations Density 0.959%

terms and concepts related to mathematical or statistical analysis and verification processes

No Comments

No Known Activations