INDEX

Explanations

information related to significant historical events and their consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 Majefty

-1.26

 pleaſure

-1.21

 Monfieur

-1.05

 themſelves

-1.05

 ſeveral

-1.05

 ſtre

-1.03

 Reſ

-1.02

 ſever

-1.01

 Diſ

-1.00

 myſelf

-1.00

POSITIVE LOGITS

 ۱۹

0.97

 २०

0.83

 ২০

0.82

一九

0.65

denas

0.60

jahr

0.60

 years

0.60

itrile

0.59

 Trump

0.58

Activations Density 0.887%

information related to significant historical events and their consequences

No Comments

No Known Activations