INDEX

Explanations

references to negative impacts or consequences

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 Conroy

-0.56

idopsis

-0.52

 bArr

-0.52

Tämä

-0.51

oflu

-0.51

 polymorphism

-0.50

bux

-0.50

helfen

-0.50

 Tilly

-0.49

žd

-0.49

POSITIVE LOGITS

 negative

3.18

 Negative

2.98

negative

2.87

Negative

2.82

 NEGATIVE

2.56

NEGATIVE

2.55

 negatives

2.54

 negativo

2.29

 negatif

2.26

 negativity

2.25

Activations Density 0.115%

references to negative impacts or consequences

No Comments

No Known Activations

references to negative impacts or consequences

No Comments

No Known Activations