INDEX

Explanations

specific names or references related to individuals or entities

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

Tokens starting with "Sh" or "Ch"

np_acts-logits-general · gemini-2.0-flash

Sh followed by vowels

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 ་་

-0.75

 faſt

-0.73

).</

-0.73

}</

-0.70

principalTable

-0.67

URBANA

-0.67

}'.

-0.67

 ―――――

-0.66

}}.

-0.65

,</

-0.65

POSITIVE LOGITS

Sh

1.00

Sh

1.00

Ch

0.99

Ch

0.94

ch

0.93

Br

0.80

Br

0.77

sh

0.77

sh

0.76

Qu

0.74

Activations Density 0.221%

specific names or references related to individuals or entities

Tokens starting with "Sh" or "Ch"

Sh followed by vowels

No Comments

No Known Activations