INDEX

Explanations

mathematical notations and equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 Reſ

-0.67

 ſta

-0.67

 ſtate

-0.66

 BoxFit

-0.66

 ſch

-0.65

 ſtand

-0.65

 ſche

-0.63

 ſever

-0.61

 ſer

-0.61

 ſen

-0.61

POSITIVE LOGITS

 nakalista

0.71

GEBURTSDATUM

0.60

AddHtmlAttribute

0.59

awaiter

0.57

ParallelGroup

0.57

SerializedSize

0.57

findpost

0.55

"]))

0.55

featureID

0.55

 مرئيه

0.54

Activations Density 1.673%

mathematical notations and equations

No Comments

No Known Activations