INDEX

Explanations

references to legal or procedural processes

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GEBURTSDATUM

-0.90

protoimpl

-0.87

 ModelExpression

-0.77

 pinulongan

-0.77

thâu

-0.69

featureID

-0.68

AndEndTag

-0.67

 opérateur

-0.67

 AssemblyVersion

-0.65

 AssemblyTitle

-0.63

POSITIVE LOGITS

mathrm

0.75

setcounter

0.72

 Audiodateien

0.69

anueva

0.62

multicolumn

0.59

raisemb

0.59

 дъ

0.58

’

0.57

SEGU

0.57

äiv

0.55

Activations Density 0.246%

references to legal or procedural processes

No Comments

No Known Activations