INDEX

Explanations

references to authors and versioning details in documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

InputTagHelper

-0.77

bootstrapcdn

-0.67

 iprot

-0.62

########.

-0.59

iNdEx

-0.56

elemField

-0.56

ngrx

-0.54

 فريبيس

-0.54

SequentialGroup

-0.54

 跳转至

-0.54

POSITIVE LOGITS

author

0.86

 Assignee

0.61

 ainfi

0.60

므로

0.58

Datuak

0.58

autorité

0.58

 Perché

0.58

 guerres

0.57

ifiquement

0.56

 UNIVERSIT

0.56

Activations Density 0.036%

references to authors and versioning details in documentation

No Comments

No Known Activations