INDEX

Explanations

mentions of the name "George"

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

twimg

-0.89

}]

-0.74

 propOrder

-0.71

|}{\

-0.71

 TextFormField

-0.70

AccessorTable

-0.70

ngdoc

-0.70

❮

-0.69

 Dign

-0.68

 Riti

-0.67

POSITIVE LOGITS

 George

4.32

George

4.00

 GEORGE

3.35

 george

3.31

george

3.09

GEORGE

2.86

 Georges

2.17

 Джор

1.99

 جورج

1.90

Georges

1.79

Activations Density 0.052%

mentions of the name "George"

No Comments

No Known Activations