INDEX

Explanations

terms related to fashion

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

gelt

-0.67

 cueva

-0.61

argout

-0.59

etCode

-0.59

имущества

-0.57

 orale

-0.56

SerializedName

-0.56

_{*}

-0.56

 retenir

-0.56

sigs

-0.56

POSITIVE LOGITS

 fashion

4.52

fashion

3.92

 Fashion

3.90

Fashion

3.76

 FASHION

3.54

FASHION

2.96

 fashions

2.90

 fash

2.48

 moda

2.26

ashions

2.25

Activations Density 0.073%

terms related to fashion

No Comments

No Known Activations