INDEX

Explanations

references to visual representations or illustrations, particularly in the context of written content

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

 csal

-0.69

 myſelf

-0.66

Osp

-0.66

SwingConstants

-0.64

 Sopho

-0.63

ihnachten

-0.63

owulf

-0.61

painel

-0.61

Skład

-0.61

ykjav

-0.61

POSITIVE LOGITS

 figure

2.47

 figures

2.35

figure

2.33

 Figure

2.16

 Figures

2.13

 FIGURES

2.09

Figure

2.08

figures

2.07

 FIGURE

1.98

Figures

1.87

Activations Density 0.127%

references to visual representations or illustrations, particularly in the context of written content

No Comments

No Known Activations