INDEX

Explanations

references to figures and diagrams within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

-0.48

GenerationType

-0.45

 Sandoval

-0.43

mitteilung

-0.40

 palha

-0.40

стар

-0.38

াত

-0.38

COUVER

-0.37

 strada

-0.37

quilo

-0.37

POSITIVE LOGITS

 Figure

3.09

Figure

2.85

 figure

2.84

Fig

2.71

figure

2.65

Fig

2.55

fig

2.35

 FIGURE

2.33

 Figures

2.27

fig

2.23

Activations Density 1.615%

references to figures and diagrams within the text

No Comments

No Known Activations