INDEX

Explanations

references to specific event categories or meetings

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 téléphonique

-0.61

ContentAlignment

-0.59

 telefónica

-0.56

 JSONException

-0.55

 tắt

-0.55

parametrize

-0.54

 AspNetCore

-0.53

änning

-0.52

CodedInputStream

-0.52

 setuptools

-0.52

POSITIVE LOGITS

 "..\..\..\

0.78

<eos>

0.71

 autorytatywna

0.71

 "..\..\

0.68

期刊论文

0.62

 дописавши

0.61

AddTagHelper

0.58

WebVitals

0.57

حياته

0.56

cshtml

0.55

Activations Density 0.275%

references to specific event categories or meetings

No Comments

No Known Activations