INDEX

Explanations

historical references and significant events related to organizations, places, and significant figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

glPopMatrix

-0.46

Pret

-0.45

IVOS

-0.45

 Pret

-0.45

nocześnie

-0.45

essen

-0.45

бір

-0.44

 Signalez

-0.44

timmt

-0.44

roslav

-0.44

POSITIVE LOGITS

 originated

1.45

 started

1.36

 originally

1.36

Originally

1.34

 Started

1.28

 began

1.28

started

1.25

Started

1.25

originally

1.25

 Originally

1.24

Activations Density 0.602%

historical references and significant events related to organizations, places, and significant figures

No Comments

No Known Activations