INDEX

Explanations

terms related to matrix operations and their impact in mathematical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 myſelf

-1.07

 itſelf

-0.98

 themſelves

-0.95

 pleaſure

-0.95

 purpoſe

-0.94

 himſelf

-0.93

 houſe

-0.91

 crdi

-0.90

 deſt

-0.89

 raiſ

-0.89

POSITIVE LOGITS

0.75

0.73

0.70

0.69

0.67

0.65

0.63

0.62

Activations Density 1.329%

terms related to matrix operations and their impact in mathematical contexts

No Comments

No Known Activations