INDEX

Explanations

specific references to tables and summarized data within documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

sist

-0.42

flo

-0.42

Географиясе

-0.41

 heapq

-0.40

flow

-0.39

 Facebook

-0.39

peel

-0.38

draw

-0.38

ập

-0.38

mere

-0.38

POSITIVE LOGITS

 table

0.82

 tables

0.73

Table

0.67

 AssemblyCulture

0.66

 tabela

0.66

 جدول

0.66

 tabla

0.65

 Table

0.64

 tabulated

0.62

Diweddarwch

0.60

Activations Density 1.182%

specific references to tables and summarized data within documents

No Comments

No Known Activations