INDEX

Explanations

terms related to hints, exotic types, and fan speeds

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

-0.65

-0.56

/*

-0.54

↵↵

-0.50

-0.48

-0.46

-0.45

/**

-0.45

<h2>

-0.45

POSITIVE LOGITS

 myſelf

1.22

 himſelf

1.18

 pleaſure

1.15

 themſelves

1.13

 purpoſe

1.10

 itſelf

1.02

 greateſt

1.01

 houſe

1.01

 leſs

1.00

 ſtate

0.98

Activations Density 0.529%

terms related to hints, exotic types, and fan speeds

No Comments

No Known Activations