INDEX

Explanations

references to the word "brilliant" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

 object

-0.43

iub

-0.40

 waste

-0.40

 mature

-0.40

 ATTEND

-0.40

 negru

-0.39

memset

-0.39

 opposing

-0.39

Arm

-0.39

impro

-0.39

POSITIVE LOGITS

Calculating

0.67

 Calculating

0.65

 calculating

0.65

lamabad

0.63

Calculate

0.60

 queſta

0.57

Calculations

0.57

calculation

0.57

Calculation

0.54

Followed

0.54

Activations Density 0.166%

references to the word "brilliant" in various contexts

No Comments

No Known Activations

references to the word "brilliant" in various contexts

No Comments

No Known Activations