INDEX

Explanations

instructions related to cooking or food preparation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

Efq

-0.82

OGND

-0.81

 NSCoder

-0.77

 fevere

-0.76

 becauſe

-0.70

 Monfieur

-0.68

providedIn

-0.68

 Theſe

-0.68

AutoresizingMask

-0.68

 onCancelled

-0.66

POSITIVE LOGITS

use

0.74

 make

0.72

do

0.71

 take

0.65

 Obrador

0.65

 remember

0.63

put

0.62

 look

0.60

try

0.60

 check

0.60

Activations Density 0.243%

instructions related to cooking or food preparation

No Comments

No Known Activations