INDEX

Explanations

occurrences of the word "starting."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

DoubleQuotes

-0.65

DNEY

-0.54

gcs

-0.54

bomba

-0.54

 estekak

-0.53

RESUMO

-0.52

aarrggbb

-0.52

HashCode

-0.52

jast

-0.51

/*

-0.50

POSITIVE LOGITS

 starting

1.14

 Starting

1.13

Starting

1.10

starting

1.04

 STARTING

1.03

Finishing

0.88

STARTING

0.86

 Finishing

0.85

 finishing

0.82

finishing

0.80

Activations Density 0.086%

occurrences of the word "starting."

No Comments

No Known Activations