INDEX

Explanations

terms related to software services or programming constructs

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

 myſelf

-0.93

 poffe

-0.86

ſelves

-0.81

 Majefty

-0.80

ſelf

-0.80

 Theſe

-0.78

 defire

-0.77

 pleaſure

-0.76

 saludo

-0.76

 Monfieur

-0.76

POSITIVE LOGITS

Service

1.19

 Service

1.04

getService

1.00

Services

0.96

 service

0.96

service

0.95

 services

0.93

SERVICE

0.92

 Services

0.92

services

0.90

Activations Density 0.031%

terms related to software services or programming constructs

No Comments

No Known Activations