INDEX

Explanations

references to biological terms and constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

↵

-0.52

are

-0.48

-0.46

-0.45

-0.43

to

-0.42

 there

-0.42

.*")]

-0.41

us

-0.40

POSITIVE LOGITS

Vidite

1.04

IndentedString

0.95

LookAnd

0.93

RectangleBorder

0.92

prefixer

0.90

Chham

0.89

Personensuche

0.89

aarrggbb

0.88

MigrationBuilder

0.87

 nakalista

0.86

Activations Density 0.827%

references to biological terms and constructs

No Comments

No Known Activations