INDEX

Explanations

references to technology and coding problems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

gameserver

-0.51

fvar

-0.45

BufferException

-0.45

saraba

-0.44

EndProject

-0.43

GenerationType

-0.43

ceğiniz

-0.42

 dunque

-0.40

kloped

-0.40

issimo

-0.40

POSITIVE LOGITS

IntoConstraints

0.82

tvguidetime

0.68

 ModelExpression

0.66

RenderAtEndOf

0.62

 dàng

0.59

findpost

0.58

 oprot

0.57

 BufferedWriter

0.56

jsonwebtoken

0.56

RectangleBorder

0.55

Activations Density 0.377%

references to technology and coding problems

No Comments

No Known Activations