INDEX

Explanations

references to unknown entities or situations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

<0x9D>

-0.63

 Dodson

-0.60

 nakalista

-0.56

<eos>

-0.55

 Neighbors

-0.55

behörde

-0.55

-0.54

Rev

-0.53

lu

-0.53

POSITIVE LOGITS

 unknown

1.50

 Unknown

1.42

unknown

1.40

 inconn

1.36

 UNKNOWN

1.34

 unknowns

1.23

Unknown

1.22

 inconnu

1.14

 desconhe

1.14

 desconocido

1.13

Activations Density 0.060%

references to unknown entities or situations

No Comments

No Known Activations