INDEX

Explanations

references to "Tra" as a prefix or part of various words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

Scoop

-0.77

 Heilig

-0.75

 Eisenberg

-0.71

 éclair

-0.70

mû

-0.67

 Keim

-0.67

<&

-0.67

 déliv

-0.67

 celo

-0.66

Sibling

-0.66

POSITIVE LOGITS

Tra

3.03

Tra

2.96

tra

2.95

tra

2.82

TRA

2.40

TRA

1.97

 trac

1.87

Trax

1.83

 Trapp

1.71

trac

1.71

Activations Density 0.067%

references to "Tra" as a prefix or part of various words

No Comments

No Known Activations