INDEX

Explanations

symbolic representations indicating emphasis or references in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 الحره

-0.60

 préc

-0.59

XmlAccessType

-0.56

Weakness

-0.55

enumi

-0.55

 betweenstory

-0.55

ữ

-0.55

everybody

-0.55

InstrumentedTest

-0.54

 AllMovie

-0.53

POSITIVE LOGITS

(;;)

0.61

INSEE

0.59

_('

0.58

″]

0.55

ukone

0.55

avir

0.54

∮

0.54

 nahilalakip

0.54

жели

0.52

Activations Density 0.126%

symbolic representations indicating emphasis or references in the text

No Comments

No Known Activations