INDEX

Explanations

tokens related to variable names and mathematical symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

 purpoſe

-1.10

 myſelf

-1.04

 pleaſure

-1.01

 faſt

-1.00

 ſeveral

-1.00

 Monfieur

-0.96

 themſelves

-0.95

 ſever

-0.92

 Beſ

-0.91

 ſame

-0.91

POSITIVE LOGITS

1.92

1.67

1.62

1.17

getZ

1.04

0.94

0.91

0.88

Activations Density 0.113%

tokens related to variable names and mathematical symbols

No Comments

No Known Activations