INDEX

Explanations

references to ownership or possession

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 Monfieur

-0.77

 Agamemnon

-0.76

 raiſ

-0.74

נטרנט

-0.73

 faſt

-0.71

menistan

-0.70

 purpoſe

-0.69

Jegyzetek

-0.69

 pleaſure

-0.66

 Allez

-0.66

POSITIVE LOGITS

his

2.24

His

2.04

HIS

2.02

His

1.97

his

1.88

HIS

1.80

her

1.54

Her

1.41

他的

1.38

 seiner

1.35

Activations Density 0.157%

references to ownership or possession

No Comments

No Known Activations