INDEX

Explanations

references to hotels and their attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

iarkan

-0.59

 ""],

-0.57

 scratched

-0.54

 насељу

-0.52

 MonoBehaviour

-0.52

 veux

-0.51

[]:

-0.51

rofoam

-0.49

RenderAtEndOf

-0.49

ofla

-0.48

POSITIVE LOGITS

 Waldorf

0.67

 EDITION

0.64

 Mandarin

0.63

 Rosewood

0.61

 Collection

0.60

Wald

0.59

 Conrad

0.59

 Fairmont

0.58

Conrad

0.58

 Kemp

0.57

Activations Density 0.154%

references to hotels and their attributes

No Comments

No Known Activations