INDEX

Explanations

references to food quality and value in restaurant reviews

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

 apellidos

-0.58

 مشين

-0.58

WebElementEntity

-0.57

 uVar

-0.56

inetic

-0.54

 băr

-0.53

festa

-0.51

perrt

-0.51

AccessorTable

-0.51

Autoritní

-0.51

POSITIVE LOGITS

 service

0.98

 value

0.89

 atmosphere

0.84

 ambience

0.82

 ambiance

0.81

 SERVICE

0.79

 Service

0.77

service

0.77

 attentive

0.72

value

0.71

Activations Density 0.115%

references to food quality and value in restaurant reviews

No Comments

No Known Activations