INDEX

Explanations

mathematical symbols and notations in equations or expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

-0.73

-0.68

-0.62

-0.61

 Anna

-0.59

-0.58

之

-0.57

-0.55

Te

-0.55

POSITIVE LOGITS

ſelves

1.22

 purpoſe

1.15

 myſelf

1.13

 raiſ

1.13

 ſche

1.10

ſelf

1.09

 iſt

1.08

 pleaſure

1.07

 whoſe

1.05

 ſtand

1.04

Activations Density 0.594%

mathematical symbols and notations in equations or expressions

No Comments

No Known Activations