INDEX

Explanations

references to code structures or syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

disposing

-0.65

Zunanje

-0.63

солю

-0.60

::=

-0.58

CopyWith

-0.58

PreferredItem

-0.56

Disposed

-0.56

:][

-0.55

dotted

-0.55

 Miscell

-0.55

POSITIVE LOGITS

[]:

1.19

 postIndex

0.87

HtmlAttribute

0.83

 CURLOPT

0.68

日閲覧

0.68

usermodel

0.67

 considérons

0.63

UpInside

0.62

RTEX

0.61

getActiveSheet

0.60

Activations Density 0.010%

references to code structures or syntax

No Comments

No Known Activations