INDEX

Explanations

terms related to coding and programming functions or components

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

opsida

-0.76

didSet

-0.72

httphttps

-0.68

Subviews

-0.63

IGraphics

-0.62

исленность

-0.61

Mil

-0.60

orescence

-0.60

<blockquote>

-0.60

̀u

-0.60

POSITIVE LOGITS

Efq

1.21

 ſche

1.18

 Monfieur

1.17

 houſe

1.16

ſelf

1.15

 pleaſure

1.05

 whoſe

1.03

 purpoſe

1.03

ſy

1.03

 Theſe

1.02

Activations Density 0.618%

terms related to coding and programming functions or components

No Comments

No Known Activations