INDEX

Explanations

phrases indicating actions or processes related to adjustment and modification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 riuscito

-0.61

 sumpay

-0.57

はじめに

-0.55

 moeite

-0.53

prüche

-0.52

 esimer

-0.52

ectady

-0.52

 bedenken

-0.51

hésitez

-0.50

 esternos

-0.50

POSITIVE LOGITS

 become

0.85

 unrecogn

0.79

 include

0.75

 something

0.74

become

0.71

 near

0.70

 suit

0.68

ConstraintMaker

0.68

 accommodate

0.67

 manageable

0.67

Activations Density 0.404%

phrases indicating actions or processes related to adjustment and modification

No Comments

No Known Activations