INDEX

Explanations

terms associated with negative outcomes or conditions

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

WireFormatLite

-0.82

tocin

-0.66

([...

-0.60

 bArr

-0.59

 onData

-0.57

 Conroy

-0.56

ึ้น

-0.56

 AssemblyProduct

-0.55

ruk

-0.55

inSlope

-0.53

POSITIVE LOGITS

 negative

1.50

NEGATIVE

1.46

 Negative

1.45

negative

1.38

 negativity

1.38

 negatives

1.36

Negative

1.32

(-)

1.28

 NEGATIVE

1.27

 negativ

1.26

Activations Density 0.259%

terms associated with negative outcomes or conditions

No Known Activations