INDEX

Explanations

terms related to schema definitions in XML and data contexts

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

 poffible

-0.88

 poff

-0.84

 Houſe

-0.80

 ſeveral

-0.79

 bicchiere

-0.74

 poffe

-0.74

#+#

-0.74

 lordship

-0.73

Efq

-0.72

 ſta

-0.71

POSITIVE LOGITS

 schema

1.55

schema

1.52

 Schema

1.52

Schema

1.51

SCHEMA

1.43

 SCHE

1.35

 schemas

1.26

 SCHEME

1.25

chema

1.22

Schemas

1.14

Activations Density 0.074%

terms related to schema definitions in XML and data contexts

No Comments

No Known Activations