INDEX

Explanations

phrases that categorize or describe types or kinds of things

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

rotum

-0.86

Дереккөздер

-0.80

 pleaſure

-0.80

 myſelf

-0.80

 houſe

-0.76

 ſta

-0.74

ViewFeatures

-0.73

+#+#

-0.73

 reaſon

-0.72

 Roach

-0.71

POSITIVE LOGITS

 KIND

1.10

 sort

1.06

 kind

1.06

 Kind

1.04

 sorta

1.00

KIND

0.97

 SORT

0.95

 Sort

0.94

kind

0.94

Kind

0.91

Activations Density 0.097%

phrases that categorize or describe types or kinds of things

No Comments

No Known Activations