INDEX

Explanations

references to query-related terms and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Sted

-0.63

tvguidetime

-0.60

StructEnd

-0.58

beforeAll

-0.57

+#+

-0.56

AnimationsModule

-0.56

 alpaca

-0.55

CVE

-0.55

 isNameExpr

-0.55

 convain

-0.54

POSITIVE LOGITS

 query

4.32

 Query

3.68

query

3.67

Query

3.36

 queries

3.35

QUERY

3.00

 Queries

2.99

 QUERY

2.94

 querying

2.68

 queried

2.67

Activations Density 0.116%

references to query-related terms and concepts

No Comments

No Known Activations