INDEX

Explanations

strong formatting tags indicating emphasis or structure in text

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.53

<0xE1>

-0.52

-0.50

-0.49

on

-0.46

-0.45

in

-0.44

POSITIVE LOGITS

 itſelf

1.50

 pleaſure

1.44

 myſelf

1.43

 ―――――

1.36

 purpoſe

1.36

 themſelves

1.36

ſelf

1.36

 Monfieur

1.35

 raiſ

1.35

 Majefty

1.34

Activations Density 0.117%

strong formatting tags indicating emphasis or structure in text

No Comments

No Known Activations