INDEX

Explanations

references to specific statistical measures or data points

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.38

 further

-0.37

 стра

-0.36

of

-0.35

for

-0.35

on

-0.35

app

-0.35

let

-0.34

↵

-0.34

 type

-0.34

POSITIVE LOGITS

AddTagHelper

1.15

StructEnd

1.15

Portale

1.13

 ModelExpression

1.11

 صوتيه

1.07

InjectAttribute

1.06

 للمعارف

1.05

IsContent

1.04

 CreateTagHelper

1.03

 "..\..\..\

1.03

Activations Density 0.487%

references to specific statistical measures or data points

No Comments

No Known Activations