INDEX

Explanations

mentions of academic experiences and affiliations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_mlp_out

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

verwijspagina

-0.69

таратура

-0.69

setVerticalGroup

-0.69

 cherchés

-0.65

 дописавши

-0.64

Abitanti

-0.63

MigrationBuilder

-0.62

UnsafeEnabled

-0.60

Pautan

-0.60

Datuak

-0.59

POSITIVE LOGITS

 graduate

1.30

 grad

1.17

graduate

1.04

 GRADUATE

1.01

 Graduate

0.99

Graduate

0.95

 Grad

0.77

grad

0.77

Grad

0.73

 doctoral

0.71

Activations Density 0.417%

mentions of academic experiences and affiliations

No Comments

No Known Activations