INDEX

Explanations

statements made by individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 بيها

-0.71

 Signalez

-0.54

fjspx

-0.53

principalTable

-0.52

SourceChecksum

-0.49

apiVersion

-0.49

Espèce

-0.49

hdys

-0.47

StructEnd

-0.46

NameInMap

-0.46

POSITIVE LOGITS

 ſche

0.64

はじめに

0.63

 Houſe

0.62

 Reſ

0.61

 auffi

0.60

 poffible

0.60

 purpoſe

0.59

piram

0.59

 ſtre

0.58

ThroughAttribute

0.57

Activations Density 0.147%

statements made by individuals

No Comments

No Known Activations