INDEX

Explanations

the word "to" and its various uses in a sentence, indicating actions or intentions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 متعلقه

-1.01

 betweenstory

-0.93

principalColumn

-0.88

Efq

-0.87

MemoryWarning

-0.87

InvalidProtocol

-0.85

ViewFeatures

-0.85

rrggbb

-0.82

 Roskov

-0.82

DoubleQuotes

-0.81

POSITIVE LOGITS

 must

0.74

Must

0.74

 Must

0.69

 needs

0.69

Gotta

0.67

 muss

0.62

 Gotta

0.62

must

0.61

 musst

0.59

 måste

0.59

Activations Density 0.157%

the word "to" and its various uses in a sentence, indicating actions or intentions

No Comments

No Known Activations