INDEX

Explanations

occurrences of the word "figure" and its variations, along with contexts involving problem-solving or understanding

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

"figure" or "fig"

np_acts-logits-general · gemini-2.0-flash

figure out / figure of

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

capital

-0.51

mailto

-0.48

 Surreal

-0.48

 virtuales

-0.47

 Xander

-0.47

 visuales

-0.47

farin

-0.47

 exile

-0.47

ellites

-0.47

beams

-0.47

POSITIVE LOGITS

 Figures

1.20

 Figure

1.15

 figures

1.14

Figures

1.09

 figure

1.07

 FIGURE

1.00

 FIGURES

0.98

Figure

0.95

fig

0.93

FIG

0.89

Activations Density 0.190%

occurrences of the word "figure" and its variations, along with contexts involving problem-solving or understanding

"figure" or "fig"

figure out / figure of

No Comments

No Known Activations