INDEX

Explanations

references to tightness or constrained conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

Pel

-0.70

 Foer

-0.66

GEBURTSDATUM

-0.64

 Steinberg

-0.64

TabIndex

-0.64

Collegamenti

-0.63

MediaStore

-0.62

inazione

-0.62

 Schaefer

-0.61

 pans

-0.60

POSITIVE LOGITS

 tight

2.13

 Tight

2.04

Tight

1.97

tight

1.92

 tighter

1.69

 tightness

1.66

 tighten

1.56

 tightened

1.55

 tightly

1.54

 tightening

1.49

Activations Density 0.108%

references to tightness or constrained conditions

No Comments

No Known Activations

references to tightness or constrained conditions

No Comments

No Known Activations