INDEX

Explanations

preferences and comparisons in choices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

</em>

-0.78

xDB

-0.69

<h3>

-0.68

Al

-0.66

Dum

-0.63

 Audiodateien

-0.63

Tom

-0.61

 James

-0.61

त्व

-0.59

POSITIVE LOGITS

 Prefer

1.55

 préfé

1.53

prefer

1.48

 prefer

1.47

 Preferred

1.47

 preferred

1.44

 Preference

1.44

 preference

1.44

 prefers

1.41

 Preferences

1.40

Activations Density 0.081%

preferences and comparisons in choices

No Comments

No Known Activations