INDEX

Explanations

terms related to individual identification and classification within various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

WithMany

-0.76

EDEFAULT

-0.66

queryInterface

-0.62



-0.61

Tikang

-0.58

kháu

-0.52

cplusplus

-0.51

frastructure

-0.51

unanje

-0.50

damente

-0.49

POSITIVE LOGITS

 individual

1.57

Individual

1.46

individual

1.40

 Individual

1.40

 INDIVIDUAL

1.25

 individually

1.24

 individualized

1.21

 Einzel

1.18

 Individ

1.16

 individuale

1.15

Activations Density 1.041%

terms related to individual identification and classification within various contexts

No Comments

No Known Activations