INDEX

Explanations

mentions of negation or denial

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 defaultstate

-0.85

 raiſ

-0.81

 autorytatywna

-0.80

ſelves

-0.80

ſelf

-0.77

parsedMessage

-0.76

neſs

-0.75

IntoConstraints

-0.74

 itſelf

-0.73

 reaſon

-0.72

POSITIVE LOGITS

Ni

1.05

ni

1.04

Ni

1.00

ne

0.85

就是

0.65

就被

0.59

нибудь

0.58

就

0.58

nl

0.55

nem

0.55

Activations Density 0.073%

mentions of negation or denial

No Comments

No Known Activations