INDEX

Explanations

specific mathematical or scientific terms and their relationships in a text

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ftagPool

-0.84

 saites

-0.64

$.

-0.62

közi

-0.60

DIPSETTING

-0.60

Indians

-0.59

ercicio

-0.59

дожник

-0.58

InitVars

-0.58

unisex

-0.58

POSITIVE LOGITS

сло

0.51

la

0.50

tan

0.49

το

0.49

tan

0.48

del

0.48

vi

0.48

ris

0.47

res

0.47

Activations Density 0.244%

specific mathematical or scientific terms and their relationships in a text

No Comments

No Known Activations