INDEX

Explanations

references to directional terms in a mathematical context

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ImageContext

-0.71

Personendaten

-0.69

parsedMessage

-0.69

pyplot

-0.68

PyExc

-0.61

GIVEREF

-0.61

Sơ

-0.60

RenderAtEndOf

-0.58

thâu

-0.58

CodedInputStream

-0.57

POSITIVE LOGITS

 anzi

0.60

 Kinney

0.59

MetaObject

0.57

issimo

0.57

 tslint

0.52

fano

0.52

 eerst

0.52

 perciò

0.52

arctic

0.52

upaten

0.51

Activations Density 0.076%

references to directional terms in a mathematical context

No Comments

No Known Activations