INDEX

Explanations

references to honor and recognition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 favor

-0.80

 color

-0.76

 labor

-0.76

 ее

-0.74

 honor

-0.72

 center

-0.69

 Ее

-0.68

 favors

-0.65

-0.64

POSITIVE LOGITS

 neighbourhoods

1.79

colour

1.78

Colour

1.75

 humour

1.74

 colours

1.74

COLOUR

1.74

 neighbourhood

1.72

 honour

1.71

 Honour

1.69

 tumour

1.69

Activations Density 0.110%

references to honor and recognition

No Comments

No Known Activations