INDEX

Explanations

phrases indicating explanations or clarifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

.」

-0.57

pear

-0.56

ẹn

-0.55

 surges

-0.55

 theme

-0.55

[]);

-0.55

\"");

-0.55

"""

-0.54

 strtok

-0.53

 themes

-0.53

POSITIVE LOGITS

verwijspagina

0.90

 cioè

0.82

 ujednoznacz

0.79



0.79

 protoimpl

0.71

ImageContext

0.71

parsedMessage

0.71

GEBURTSDATUM

0.67

也就是说

0.67

 means

0.66

Activations Density 0.306%

phrases indicating explanations or clarifications

No Comments

No Known Activations