INDEX

Explanations

references to specific identifiers or variables in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 InputDecoration

-0.74

 HasFactory

-0.68

RenderAtEndOf

-0.64

 autorytatywna

-0.63

MemoryWarning

-0.62

 GetEnumerator

-0.62

SpringBootTest

-0.61

帖最后由

-0.61

DockStyle

-0.60

AddTagHelper

-0.60

POSITIVE LOGITS

 AssemblyTitle

0.54

 विश्वसनीयता

0.44

 picket

0.44

asz

0.43

OfMonth

0.43

Wass

0.42

łe

0.42

ename

0.42

 beginnetje

0.42

=:

0.41

Activations Density 0.130%

references to specific identifiers or variables in a programming context

No Comments

No Known Activations