INDEX

Explanations

references to the name "Martin" in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Efq

-1.15

 ſta

-1.04

 myſelf

-1.02

 pleaſure

-0.99

fjspx

-0.97

 poffible

-0.96

 tranſ

-0.95

 uſed

-0.95

 houſe

-0.95

 faſt

-0.94

POSITIVE LOGITS

се

0.69

Leave

0.67

Check

0.67

Always

0.66

 Leave

0.59

0.58

 Always

0.57

性

0.56

 Check

0.54

Send

0.54

Activations Density 0.134%

references to the name "Martin" in various contexts

No Comments

No Known Activations