INDEX

Explanations

references to the word "crack" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

Personensuche

-0.78

 vuitton

-0.74

internalType

-0.70

/*

-0.66

ngdoc

-0.66

MessageTagHelper

-0.65

ofType

-0.65

{{$

-0.63

>--}}

-0.63

ejs

-0.62

POSITIVE LOGITS

 crack

3.49

crack

3.06

 cracks

3.03

 Crack

2.94

 CRACK

2.94

 cracked

2.77

 cracking

2.73

Crack

2.73

 Cracks

2.60

 Cracking

2.48

Activations Density 0.080%

references to the word "crack" in various contexts

No Comments

No Known Activations