INDEX

Explanations

information regarding disputes and conflicts

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

 CreateTagHelper

-0.58

ثيق

-0.57

createServer

-0.56

 ListTile

-0.54

 cair

-0.52

ListTile

-0.52

 InputDecoration

-0.50

TIL

-0.50

 GeoNames

-0.50

 censiti

-0.50

POSITIVE LOGITS

 developed

0.82

 unfolded

0.77

 разви

0.75

 progressed

0.75

 unfolds

0.71

developed

0.71

 develops

0.69

 gelişti

0.69

 develop

0.68

 DEVELOP

0.68

Activations Density 1.011%

information regarding disputes and conflicts

No Comments

No Known Activations