INDEX

Explanations

occurrences of the word "instance" and its variations to track references to specific objects or occurrences in a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Efq

-1.53

 Monfieur

-1.36

=$?

-1.35

 Theſe

-1.35

 photolibrary

-1.30

 myſelf

-1.29

 ―――――

-1.29

 themſelves

-1.27

 Anſ

-1.27

$_"

-1.25

POSITIVE LOGITS

0.79

0.75

0.74

0.73

0.70

 instance

0.70

San

0.67

 instances

0.67

0.66

Activations Density 0.142%

occurrences of the word "instance" and its variations to track references to specific objects or occurrences in a context

No Comments

No Known Activations