INDEX

Explanations

references to "bottom" in various contexts, often in relation to positioning or layout

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ⓧ

-0.86

 Réponses

-0.79

ⓘ

-0.77

gridx

-0.76

numerusform

-0.75

 Winaray

-0.74

 MessageBoxIcon

-0.74

riezmann

-0.72

Erika

-0.70

rinfo

-0.69

POSITIVE LOGITS

 bottom

2.45

 Bottom

2.33

bottom

2.33

 BOTTOM

2.30

Bottom

2.13

BOTTOM

2.06

 bottoms

2.02

 botto

1.68

botto

1.44

底

1.24

Activations Density 0.044%

references to "bottom" in various contexts, often in relation to positioning or layout

No Comments

No Known Activations