INDEX

Explanations

references to figures, diagrams, or visual representations in documents

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

Refers to figures or diagrams

np_acts-logits-general · gemini-2.0-flash

in FIGURE / FIG references

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

GenerationType

-0.65

 vPvB

-0.65

GEBURTSDATUM

-0.64

 &___

-0.60

AxisAlignment

-0.58

ContentAsync

-0.55

COUVER

-0.55

 للمعارف

-0.55

</thead>

-0.55

 internetowa

-0.54

POSITIVE LOGITS

 Figure

2.60

Figure

2.45

Fig

2.09

 figure

2.08

Fig

1.96

figure

1.92

 Figures

1.71

fig

1.67

fig

1.62

 FIGURE

1.62

Activations Density 1.091%

references to figures, diagrams, or visual representations in documents

Refers to figures or diagrams

in FIGURE / FIG references

No Comments

No Known Activations