INDEX

Explanations

the word "pre" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

BindingResult

-0.73

formik

-0.66

NgModule

-0.66

=()

-0.62

sqcup

-0.59

Demografie

-0.58

ÍO

-0.56

migrationBuilder

-0.56

Lycka

-0.56

Spoljašnje

-0.55

POSITIVE LOGITS

Pre

3.86

pre

3.85

Pre

3.81

PRE

3.44

PRE

3.42

pre

3.35

 pré

2.89

 Pré

2.50

Pré

2.42

pré

2.38

Activations Density 0.077%

the word "pre" in various contexts

No Comments

No Known Activations