INDEX

Explanations

phrases that indicate possession or attribution of qualities or items

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

Efq

-0.79

 fhort

-0.76

 pleaſure

-0.74

 occaf

-0.67

 houſe

-0.66

 purpoſe

-0.65

 fileSize

-0.64

 themſelves

-0.62

 Houſe

-0.62

 Majefty

-0.62

POSITIVE LOGITS

TagMode

0.94

 nahilalakip

0.91

 Normdatei

0.86

+#+#

0.86

ApiProperty

0.85

ReusableCell

0.84

principalColumn

0.82

 AspNetCore

0.81

 dintre

0.80

__(/*!

0.79

Activations Density 0.144%

phrases that indicate possession or attribution of qualities or items

No Comments

No Known Activations