INDEX

Explanations

place names and specific geographical references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

AutoField

-0.55

CppMethod

-0.55

nonatomic

-0.54

ulco

-0.48

Kalb

-0.47

multirow

-0.47

eward

-0.46

devamını

-0.46

[](

-0.45

TestTools

-0.45

POSITIVE LOGITS

 Dakota

0.88

Winnipeg

0.83

Dakota

0.81

 Winnipeg

0.79

 Manitoba

0.79

 Fargo

0.76

 Bismarck

0.71

 Sioux

0.67

 dakota

0.63

asteroide

0.62

Activations Density 0.095%

place names and specific geographical references

No Comments

No Known Activations