INDEX

Explanations

mathematical expressions and definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

...

-0.52

BOSTON

-0.48

ngdoc

-0.47

 NgModule

-0.47

…

-0.44

openapi

-0.44

co

-0.43

 sample

-0.43

stand

-0.43

uschen

-0.43

POSITIVE LOGITS

tagHelperRunner

0.95

Efq

0.90

+#+#

0.85

 Majefty

0.77

 Houſe

0.77

 fevere

0.69

 Monfieur

0.69

 doubtnut

0.69

 متعلقه

0.68

 houſe

0.68

Activations Density 0.194%

mathematical expressions and definitions

No Comments

No Known Activations