INDEX

Explanations

references to data representations in a structured context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 فريبيس

-0.62

ArrowToggle

-0.61

 fragrance

-0.52

friend

-0.50

QMetaType

-0.50

potranspiration

-0.49

 يتيمه

-0.49

Архівовано

-0.49

 الموقع

-0.48

âtre

-0.47

POSITIVE LOGITS

 panel

4.43

panel

3.89

 Panel

3.86

Panel

3.58

 PANEL

3.46

 panels

3.35

PANEL

3.11

 Panels

2.98

panels

2.69

 panelists

2.60

Activations Density 0.180%

references to data representations in a structured context

No Comments

No Known Activations