INDEX

Explanations

mentions of locations and dining experiences

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 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

 Paglinawan

-0.71

tvguidetime

-0.61

 composizione

-0.61

 Jefus

-0.60

ValueStyle

-0.59

iblichen

-0.59

InstanceState

-0.57

 Theſe

-0.57

FunctionFlags

-0.56

URLException

-0.55

POSITIVE LOGITS

 McDonald

1.15

 McDonalds

1.08

 Starbucks

1.03

 fast

1.01

McDonald

0.98

KFC

0.97

 Dunkin

0.97

 chain

0.95

 Fast

0.89

 Pizza

0.88

Activations Density 0.182%

mentions of locations and dining experiences

No Comments

No Known Activations