INDEX

Explanations

references to governmental or state-related terms and their implications

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

 Piac

-0.84

}),

-0.80

 fusca

-0.79

 Rouen

-0.76

EMPO

-0.75

 encom

-0.74

 Jezus

-0.73

 Recife

-0.71

 Amiens

-0.70

 Avignon

-0.70

POSITIVE LOGITS

 State

1.66

 state

1.59

 STATE

1.49

 States

1.42

 states

1.38

states

1.38

state

1.37

State

1.36

STATE

1.33

States

1.31

Activations Density 0.136%

references to governmental or state-related terms and their implications

No Comments

No Known Activations