INDEX

Explanations

words related to identity and naming conventions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 saites

-0.88

outchouc

-0.77

 Butterfield

-0.73

IUrlHelper

-0.73

RTLD

-0.73

ViewFeatures

-0.73

ukunft

-0.71

 Мексичка

-0.70

Demografía

-0.69

uroy

-0.69

POSITIVE LOGITS

fen

0.96

en

0.95

eden

0.93

hen

0.92

ghen

0.88

ellen

0.85

nen

0.84

EN

0.84

zen

0.84

ken

0.83

Activations Density 0.473%

words related to identity and naming conventions

No Comments

No Known Activations