INDEX

Explanations

elements related to data structure or analysis contexts, including tables and descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

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

InjectAttribute

-0.70

TagMode

-0.67

 lenker

-0.63

Jereo

-0.61

Kjelder

-0.61

 kaarangay

-0.60

AddTagHelper

-0.60

 AssemblyCulture

-0.59

الإنجليزية

-0.58

RTEX

-0.57

POSITIVE LOGITS

 highlights

0.58

UTER

0.58

 characteristics

0.53

simos

0.53

envol

0.52

CUIT

0.51

ellini

0.50

 rationale

0.50

addAll

0.50

NAN

0.50

Activations Density 0.464%

elements related to data structure or analysis contexts, including tables and descriptions

No Comments

No Known Activations