INDEX

Explanations

code structures that define boolean variables and their conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Yes

-0.55

OLOGIES

-0.53

правля

-0.49

挙げ

-0.48

 näm

-0.48

[++

-0.48

-0.47

｀

-0.47

 saja

-0.46

POSITIVE LOGITS

 pinulongan

0.82

Personensuche

0.69

RegressionTest

0.69

 purpoſe

0.69

Gambas

0.69

 ſche

0.68

 sement

0.67

Put

0.67

 ſtate

0.66

Svg

0.66

Activations Density 0.291%

code structures that define boolean variables and their conditions

No Comments

No Known Activations