INDEX

Explanations

assertions and statements related to functionality or effectiveness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

FormTagHelper

-0.62

themselves

-0.60

twe

-0.57

Atentamente

-0.57

 eivät

-0.57

 zaragoza

-0.57

 lisäksi

-0.55

nemonic

-0.55

mitian

-0.54

 themselves

-0.54

POSITIVE LOGITS

its

0.91

它

0.88

Its

0.83

它的

0.82

Its

0.81

它

0.77

SharedCtor

0.72

 snowing

0.70

it

0.68

它是

0.67

Activations Density 0.663%

assertions and statements related to functionality or effectiveness

No Comments

No Known Activations