INDEX

Explanations

references to channels in media contexts

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

 disambiguazione

-0.71

jsonwebtoken

-0.67

 Majefty

-0.67

 StatelessWidget

-0.67

Efq

-0.66

 للمعارف

-0.65

 provisoire

-0.64

 étoit

-0.62

waw

-0.62

 auroit

-0.61

POSITIVE LOGITS

 channel

4.64

 channels

4.04

 Channel

3.97

channel

3.95

Channel

3.65

 CHANNEL

3.63

 Channels

3.57

channels

3.40

CHANNEL

3.23

Channels

3.19

Activations Density 0.061%

references to channels in media contexts

No Comments

No Known Activations