INDEX

Explanations

references to the name "Ed" or related terms, particularly in contexts involving actions or descriptors associated with individuals named Ed

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 怎样

-0.68

 tartalomajánló

-0.66

 <=",

-0.57

 STRIP

-0.56

phazard

-0.54

CodeAttribute

-0.54

Strip

-0.54

BASELINE

-0.53

herit

-0.52

IBOutlet

-0.52

POSITIVE LOGITS

dies

0.63

gerton

0.62

ouard

0.59

 Sheeran

0.59

war

0.57

//

0.57

 ecco

0.57

gings

0.56

Décès

0.55

 Paglinawan

0.55

Activations Density 0.128%

references to the name "Ed" or related terms, particularly in contexts involving actions or descriptors associated with individuals named Ed

No Comments

No Known Activations