INDEX

Explanations

instances of words related to choice and selection

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 terça

-0.63

ţiile

-0.62

 teratur

-0.61

 fapt

-0.58

remia

-0.58

 Barclay

-0.58

simd

-0.57

 dumne

-0.57

dyti

-0.56

 resident

-0.56

POSITIVE LOGITS

 choose

2.98

choose

2.89

 Choose

2.73

Choose

2.71

 chooses

2.66

 choosing

2.60

choosing

2.53

 CHOOSE

2.42

 Choosing

2.40

 chose

2.31

Activations Density 0.095%

instances of words related to choice and selection

No Comments

No Known Activations