INDEX

Explanations

references to specific examples or case studies related to research or explanations

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

 Jefus

-0.74

InjectAttribute

-0.71

 ſeveral

-0.68

 NgModule

-0.65

 himſelf

-0.64

 themſelves

-0.64

 Majefty

-0.63

 ſtand

-0.62

 ſhould

-0.62

 ſhall

-0.60

POSITIVE LOGITS

<![

0.69

alnya

0.65

 kasarigan

0.64

клопе

0.63

makeText

0.60

InlineData

0.60

grès

0.59

}\|

0.58

GenerationType

0.58

eg

0.57

Activations Density 0.143%

references to specific examples or case studies related to research or explanations

No Comments

No Known Activations