INDEX

Explanations

names and terms related to legal proceedings and individuals involved in them

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 genero

-0.52

ARDI

-0.44

 lente

-0.43

 AssemblyTitle

-0.43

++

-0.42

rds

-0.42

removeChild

-0.42

ത്

-0.42

ulo

-0.42

 caring

-0.41

POSITIVE LOGITS

DebuggerNonUser

0.86

hObject

0.79

ParallelGroup

0.78

GEBURTSDATUM

0.78

CppMethod

0.78

principalColumn

0.75

ThroughAttribute

0.74

IVEREF

0.74

 nahilalakip

0.72

 protoimpl

0.72

Activations Density 0.998%

names and terms related to legal proceedings and individuals involved in them

No Comments

No Known Activations